the three descriptive research methods

• Skip to main content
• Skip to primary sidebar
• Skip to footer
• QuestionPro

• Solutions Industries Gaming Automotive Sports and events Education Government Travel & Hospitality Financial Services Healthcare Cannabis Technology Use Case NPS+ Communities Audience Contactless surveys Mobile LivePolls Member Experience GDPR Positive People Science 360 Feedback Surveys
• Resources Blog eBooks Survey Templates Case Studies Training Help center

Home Market Research

Descriptive Research: Definition, Characteristics, Methods + Examples

Suppose an apparel brand wants to understand the fashion purchasing trends among New York’s buyers, then it must conduct a demographic survey of the specific region, gather population data, and then conduct descriptive research on this demographic segment.

The study will then uncover details on “what is the purchasing pattern of New York buyers,” but will not cover any investigative information about “ why ” the patterns exist. Because for the apparel brand trying to break into this market, understanding the nature of their market is the study’s main goal. Let’s talk about it.

What is descriptive research?

Descriptive research is a research method describing the characteristics of the population or phenomenon studied. This descriptive methodology focuses more on the “what” of the research subject than the “why” of the research subject.

The method primarily focuses on describing the nature of a demographic segment without focusing on “why” a particular phenomenon occurs. In other words, it “describes” the research subject without covering “why” it happens.

Characteristics of descriptive research

The term descriptive research then refers to research questions, the design of the study, and data analysis conducted on that topic. We call it an observational research method because none of the research study variables are influenced in any capacity.

Some distinctive characteristics of descriptive research are:

• Quantitative research: It is a quantitative research method that attempts to collect quantifiable information for statistical analysis of the population sample. It is a popular market research tool that allows us to collect and describe the demographic segment’s nature.
• Uncontrolled variables: In it, none of the variables are influenced in any way. This uses observational methods to conduct the research. Hence, the nature of the variables or their behavior is not in the hands of the researcher.
• Cross-sectional studies: It is generally a cross-sectional study where different sections belonging to the same group are studied.
• The basis for further research: Researchers further research the data collected and analyzed from descriptive research using different research techniques. The data can also help point towards the types of research methods used for the subsequent research.

Applications of descriptive research with examples

A descriptive research method can be used in multiple ways and for various reasons. Before getting into any survey , though, the survey goals and survey design are crucial. Despite following these steps, there is no way to know if one will meet the research outcome. How to use descriptive research? To understand the end objective of research goals, below are some ways organizations currently use descriptive research today:

• Define respondent characteristics: The aim of using close-ended questions is to draw concrete conclusions about the respondents. This could be the need to derive patterns, traits, and behaviors of the respondents. It could also be to understand from a respondent their attitude, or opinion about the phenomenon. For example, understand millennials and the hours per week they spend browsing the internet. All this information helps the organization researching to make informed business decisions.
• Measure data trends: Researchers measure data trends over time with a descriptive research design’s statistical capabilities. Consider if an apparel company researches different demographics like age groups from 24-35 and 36-45 on a new range launch of autumn wear. If one of those groups doesn’t take too well to the new launch, it provides insight into what clothes are like and what is not. The brand drops the clothes and apparel that customers don’t like.
• Conduct comparisons: Organizations also use a descriptive research design to understand how different groups respond to a specific product or service. For example, an apparel brand creates a survey asking general questions that measure the brand’s image. The same study also asks demographic questions like age, income, gender, geographical location, geographic segmentation , etc. This consumer research helps the organization understand what aspects of the brand appeal to the population and what aspects do not. It also helps make product or marketing fixes or even create a new product line to cater to high-growth potential groups.
• Validate existing conditions: Researchers widely use descriptive research to help ascertain the research object’s prevailing conditions and underlying patterns. Due to the non-invasive research method and the use of quantitative observation and some aspects of qualitative observation , researchers observe each variable and conduct an in-depth analysis . Researchers also use it to validate any existing conditions that may be prevalent in a population.
• Conduct research at different times: The analysis can be conducted at different periods to ascertain any similarities or differences. This also allows any number of variables to be evaluated. For verification, studies on prevailing conditions can also be repeated to draw trends.

Advantages of descriptive research

Some of the significant advantages of descriptive research are:

• Data collection: A researcher can conduct descriptive research using specific methods like observational method, case study method, and survey method. Between these three, all primary data collection methods are covered, which provides a lot of information. This can be used for future research or even for developing a hypothesis for your research object.
• Varied: Since the data collected is qualitative and quantitative, it gives a holistic understanding of a research topic. The information is varied, diverse, and thorough.
• Natural environment: Descriptive research allows for the research to be conducted in the respondent’s natural environment, which ensures that high-quality and honest data is collected.
• Quick to perform and cheap: As the sample size is generally large in descriptive research, the data collection is quick to conduct and is inexpensive.

Descriptive research methods

There are three distinctive methods to conduct descriptive research. They are:

Observational method

The observational method is the most effective method to conduct this research, and researchers make use of both quantitative and qualitative observations.

A quantitative observation is the objective collection of data primarily focused on numbers and values. It suggests “associated with, of or depicted in terms of a quantity.” Results of quantitative observation are derived using statistical and numerical analysis methods. It implies observation of any entity associated with a numeric value such as age, shape, weight, volume, scale, etc. For example, the researcher can track if current customers will refer the brand using a simple Net Promoter Score question .

Qualitative observation doesn’t involve measurements or numbers but instead just monitoring characteristics. In this case, the researcher observes the respondents from a distance. Since the respondents are in a comfortable environment, the characteristics observed are natural and effective. In a descriptive research design, the researcher can choose to be either a complete observer, an observer as a participant, a participant as an observer, or a full participant. For example, in a supermarket, a researcher can from afar monitor and track the customers’ selection and purchasing trends. This offers a more in-depth insight into the purchasing experience of the customer.

Case study method

Case studies involve in-depth research and study of individuals or groups. Case studies lead to a hypothesis and widen a further scope of studying a phenomenon. However, case studies should not be used to determine cause and effect as they can’t make accurate predictions because there could be a bias on the researcher’s part. The other reason why case studies are not a reliable way of conducting descriptive research is that there could be an atypical respondent in the survey. Describing them leads to weak generalizations and moving away from external validity.

Survey research

In survey research, respondents answer through surveys or questionnaires or polls . They are a popular market research tool to collect feedback from respondents. A study to gather useful data should have the right survey questions. It should be a balanced mix of open-ended questions and close ended-questions . The survey method can be conducted online or offline, making it the go-to option for descriptive research where the sample size is enormous.

Examples of descriptive research

Some examples of descriptive research are:

• A specialty food group launching a new range of barbecue rubs would like to understand what flavors of rubs are favored by different people. To understand the preferred flavor palette, they conduct this type of research study using various methods like observational methods in supermarkets. By also surveying while collecting in-depth demographic information, offers insights about the preference of different markets. This can also help tailor make the rubs and spreads to various preferred meats in that demographic. Conducting this type of research helps the organization tweak their business model and amplify marketing in core markets.
• Another example of where this research can be used is if a school district wishes to evaluate teachers’ attitudes about using technology in the classroom. By conducting surveys and observing their comfortableness using technology through observational methods, the researcher can gauge what they can help understand if a full-fledged implementation can face an issue. This also helps in understanding if the students are impacted in any way with this change.

Some other research problems and research questions that can lead to descriptive research are:

• Market researchers want to observe the habits of consumers.
• A company wants to evaluate the morale of its staff.
• A school district wants to understand if students will access online lessons rather than textbooks.
• To understand if its wellness questionnaire programs enhance the overall health of the employees.

FREE TRIAL         LEARN MORE

MORE LIKE THIS

NPS Survey Platform: Types, Tips, 11 Best Platforms & Tools

Apr 26, 2024

User Journey vs User Flow: Differences and Similarities

Best 7 Gap Analysis Tools to Empower Your Business

Apr 25, 2024

12 Best Employee Survey Tools for Organizational Excellence

Other categories.

• Academic Research
• Artificial Intelligence
• Assessments
• Brand Awareness
• Case Studies
• Communities
• Consumer Insights
• Customer effort score
• Customer Engagement
• Customer Experience
• Customer Loyalty
• Customer Research
• Customer Satisfaction
• Employee Benefits
• Employee Engagement
• Employee Retention
• Friday Five
• General Data Protection Regulation
• Insights Hub
• Life@QuestionPro
• Market Research
• Mobile diaries
• Mobile Surveys
• New Features
• Online Communities
• Question Types
• Questionnaire
• QuestionPro Products
• Release Notes
• Research Tools and Apps
• Revenue at Risk
• Survey Templates
• Training Tips
• Uncategorized
• Video Learning Series
• What’s Coming Up
• Workforce Intelligence

• Privacy Policy

Home » Descriptive Research Design – Types, Methods and Examples

Descriptive Research Design – Types, Methods and Examples

Table of Contents

Descriptive Research Design

Definition:

Descriptive research design is a type of research methodology that aims to describe or document the characteristics, behaviors, attitudes, opinions, or perceptions of a group or population being studied.

Descriptive research design does not attempt to establish cause-and-effect relationships between variables or make predictions about future outcomes. Instead, it focuses on providing a detailed and accurate representation of the data collected, which can be useful for generating hypotheses, exploring trends, and identifying patterns in the data.

Types of Descriptive Research Design

Types of Descriptive Research Design are as follows:

Cross-sectional Study

This involves collecting data at a single point in time from a sample or population to describe their characteristics or behaviors. For example, a researcher may conduct a cross-sectional study to investigate the prevalence of certain health conditions among a population, or to describe the attitudes and beliefs of a particular group.

Longitudinal Study

This involves collecting data over an extended period of time, often through repeated observations or surveys of the same group or population. Longitudinal studies can be used to track changes in attitudes, behaviors, or outcomes over time, or to investigate the effects of interventions or treatments.

This involves an in-depth examination of a single individual, group, or situation to gain a detailed understanding of its characteristics or dynamics. Case studies are often used in psychology, sociology, and business to explore complex phenomena or to generate hypotheses for further research.

Survey Research

This involves collecting data from a sample or population through standardized questionnaires or interviews. Surveys can be used to describe attitudes, opinions, behaviors, or demographic characteristics of a group, and can be conducted in person, by phone, or online.

Observational Research

This involves observing and documenting the behavior or interactions of individuals or groups in a natural or controlled setting. Observational studies can be used to describe social, cultural, or environmental phenomena, or to investigate the effects of interventions or treatments.

Correlational Research

This involves examining the relationships between two or more variables to describe their patterns or associations. Correlational studies can be used to identify potential causal relationships or to explore the strength and direction of relationships between variables.

Data Analysis Methods

Descriptive research design data analysis methods depend on the type of data collected and the research question being addressed. Here are some common methods of data analysis for descriptive research:

Descriptive Statistics

This method involves analyzing data to summarize and describe the key features of a sample or population. Descriptive statistics can include measures of central tendency (e.g., mean, median, mode) and measures of variability (e.g., range, standard deviation).

Cross-tabulation

This method involves analyzing data by creating a table that shows the frequency of two or more variables together. Cross-tabulation can help identify patterns or relationships between variables.

Content Analysis

This method involves analyzing qualitative data (e.g., text, images, audio) to identify themes, patterns, or trends. Content analysis can be used to describe the characteristics of a sample or population, or to identify factors that influence attitudes or behaviors.

Qualitative Coding

This method involves analyzing qualitative data by assigning codes to segments of data based on their meaning or content. Qualitative coding can be used to identify common themes, patterns, or categories within the data.

Visualization

This method involves creating graphs or charts to represent data visually. Visualization can help identify patterns or relationships between variables and make it easier to communicate findings to others.

Comparative Analysis

This method involves comparing data across different groups or time periods to identify similarities and differences. Comparative analysis can help describe changes in attitudes or behaviors over time or differences between subgroups within a population.

Applications of Descriptive Research Design

Descriptive research design has numerous applications in various fields. Some of the common applications of descriptive research design are:

• Market research: Descriptive research design is widely used in market research to understand consumer preferences, behavior, and attitudes. This helps companies to develop new products and services, improve marketing strategies, and increase customer satisfaction.
• Health research: Descriptive research design is used in health research to describe the prevalence and distribution of a disease or health condition in a population. This helps healthcare providers to develop prevention and treatment strategies.
• Educational research: Descriptive research design is used in educational research to describe the performance of students, schools, or educational programs. This helps educators to improve teaching methods and develop effective educational programs.
• Social science research: Descriptive research design is used in social science research to describe social phenomena such as cultural norms, values, and beliefs. This helps researchers to understand social behavior and develop effective policies.
• Public opinion research: Descriptive research design is used in public opinion research to understand the opinions and attitudes of the general public on various issues. This helps policymakers to develop effective policies that are aligned with public opinion.
• Environmental research: Descriptive research design is used in environmental research to describe the environmental conditions of a particular region or ecosystem. This helps policymakers and environmentalists to develop effective conservation and preservation strategies.

Descriptive Research Design Examples

Here are some real-time examples of descriptive research designs:

• A restaurant chain wants to understand the demographics and attitudes of its customers. They conduct a survey asking customers about their age, gender, income, frequency of visits, favorite menu items, and overall satisfaction. The survey data is analyzed using descriptive statistics and cross-tabulation to describe the characteristics of their customer base.
• A medical researcher wants to describe the prevalence and risk factors of a particular disease in a population. They conduct a cross-sectional study in which they collect data from a sample of individuals using a standardized questionnaire. The data is analyzed using descriptive statistics and cross-tabulation to identify patterns in the prevalence and risk factors of the disease.
• An education researcher wants to describe the learning outcomes of students in a particular school district. They collect test scores from a representative sample of students in the district and use descriptive statistics to calculate the mean, median, and standard deviation of the scores. They also create visualizations such as histograms and box plots to show the distribution of scores.
• A marketing team wants to understand the attitudes and behaviors of consumers towards a new product. They conduct a series of focus groups and use qualitative coding to identify common themes and patterns in the data. They also create visualizations such as word clouds to show the most frequently mentioned topics.
• An environmental scientist wants to describe the biodiversity of a particular ecosystem. They conduct an observational study in which they collect data on the species and abundance of plants and animals in the ecosystem. The data is analyzed using descriptive statistics to describe the diversity and richness of the ecosystem.

How to Conduct Descriptive Research Design

To conduct a descriptive research design, you can follow these general steps:

• Define your research question: Clearly define the research question or problem that you want to address. Your research question should be specific and focused to guide your data collection and analysis.
• Choose your research method: Select the most appropriate research method for your research question. As discussed earlier, common research methods for descriptive research include surveys, case studies, observational studies, cross-sectional studies, and longitudinal studies.
• Design your study: Plan the details of your study, including the sampling strategy, data collection methods, and data analysis plan. Determine the sample size and sampling method, decide on the data collection tools (such as questionnaires, interviews, or observations), and outline your data analysis plan.
• Collect data: Collect data from your sample or population using the data collection tools you have chosen. Ensure that you follow ethical guidelines for research and obtain informed consent from participants.
• Analyze data: Use appropriate statistical or qualitative analysis methods to analyze your data. As discussed earlier, common data analysis methods for descriptive research include descriptive statistics, cross-tabulation, content analysis, qualitative coding, visualization, and comparative analysis.
• I nterpret results: Interpret your findings in light of your research question and objectives. Identify patterns, trends, and relationships in the data, and describe the characteristics of your sample or population.
• Draw conclusions and report results: Draw conclusions based on your analysis and interpretation of the data. Report your results in a clear and concise manner, using appropriate tables, graphs, or figures to present your findings. Ensure that your report follows accepted research standards and guidelines.

When to Use Descriptive Research Design

Descriptive research design is used in situations where the researcher wants to describe a population or phenomenon in detail. It is used to gather information about the current status or condition of a group or phenomenon without making any causal inferences. Descriptive research design is useful in the following situations:

• Exploratory research: Descriptive research design is often used in exploratory research to gain an initial understanding of a phenomenon or population.
• Identifying trends: Descriptive research design can be used to identify trends or patterns in a population, such as changes in consumer behavior or attitudes over time.
• Market research: Descriptive research design is commonly used in market research to understand consumer preferences, behavior, and attitudes.
• Health research: Descriptive research design is useful in health research to describe the prevalence and distribution of a disease or health condition in a population.
• Social science research: Descriptive research design is used in social science research to describe social phenomena such as cultural norms, values, and beliefs.
• Educational research: Descriptive research design is used in educational research to describe the performance of students, schools, or educational programs.

Purpose of Descriptive Research Design

The main purpose of descriptive research design is to describe and measure the characteristics of a population or phenomenon in a systematic and objective manner. It involves collecting data that describe the current status or condition of the population or phenomenon of interest, without manipulating or altering any variables.

The purpose of descriptive research design can be summarized as follows:

• To provide an accurate description of a population or phenomenon: Descriptive research design aims to provide a comprehensive and accurate description of a population or phenomenon of interest. This can help researchers to develop a better understanding of the characteristics of the population or phenomenon.
• To identify trends and patterns: Descriptive research design can help researchers to identify trends and patterns in the data, such as changes in behavior or attitudes over time. This can be useful for making predictions and developing strategies.
• To generate hypotheses: Descriptive research design can be used to generate hypotheses or research questions that can be tested in future studies. For example, if a descriptive study finds a correlation between two variables, this could lead to the development of a hypothesis about the causal relationship between the variables.
• To establish a baseline: Descriptive research design can establish a baseline or starting point for future research. This can be useful for comparing data from different time periods or populations.

Characteristics of Descriptive Research Design

Descriptive research design has several key characteristics that distinguish it from other research designs. Some of the main characteristics of descriptive research design are:

• Objective : Descriptive research design is objective in nature, which means that it focuses on collecting factual and accurate data without any personal bias. The researcher aims to report the data objectively without any personal interpretation.
• Non-experimental: Descriptive research design is non-experimental, which means that the researcher does not manipulate any variables. The researcher simply observes and records the behavior or characteristics of the population or phenomenon of interest.
• Quantitative : Descriptive research design is quantitative in nature, which means that it involves collecting numerical data that can be analyzed using statistical techniques. This helps to provide a more precise and accurate description of the population or phenomenon.
• Cross-sectional: Descriptive research design is often cross-sectional, which means that the data is collected at a single point in time. This can be useful for understanding the current state of the population or phenomenon, but it may not provide information about changes over time.
• Large sample size: Descriptive research design typically involves a large sample size, which helps to ensure that the data is representative of the population of interest. A large sample size also helps to increase the reliability and validity of the data.
• Systematic and structured: Descriptive research design involves a systematic and structured approach to data collection, which helps to ensure that the data is accurate and reliable. This involves using standardized procedures for data collection, such as surveys, questionnaires, or observation checklists.

Advantages of Descriptive Research Design

Descriptive research design has several advantages that make it a popular choice for researchers. Some of the main advantages of descriptive research design are:

• Provides an accurate description: Descriptive research design is focused on accurately describing the characteristics of a population or phenomenon. This can help researchers to develop a better understanding of the subject of interest.
• Easy to conduct: Descriptive research design is relatively easy to conduct and requires minimal resources compared to other research designs. It can be conducted quickly and efficiently, and data can be collected through surveys, questionnaires, or observations.
• Useful for generating hypotheses: Descriptive research design can be used to generate hypotheses or research questions that can be tested in future studies. For example, if a descriptive study finds a correlation between two variables, this could lead to the development of a hypothesis about the causal relationship between the variables.
• Large sample size : Descriptive research design typically involves a large sample size, which helps to ensure that the data is representative of the population of interest. A large sample size also helps to increase the reliability and validity of the data.
• Can be used to monitor changes : Descriptive research design can be used to monitor changes over time in a population or phenomenon. This can be useful for identifying trends and patterns, and for making predictions about future behavior or attitudes.
• Can be used in a variety of fields : Descriptive research design can be used in a variety of fields, including social sciences, healthcare, business, and education.

Limitation of Descriptive Research Design

Descriptive research design also has some limitations that researchers should consider before using this design. Some of the main limitations of descriptive research design are:

• Cannot establish cause and effect: Descriptive research design cannot establish cause and effect relationships between variables. It only provides a description of the characteristics of the population or phenomenon of interest.
• Limited generalizability: The results of a descriptive study may not be generalizable to other populations or situations. This is because descriptive research design often involves a specific sample or situation, which may not be representative of the broader population.
• Potential for bias: Descriptive research design can be subject to bias, particularly if the researcher is not objective in their data collection or interpretation. This can lead to inaccurate or incomplete descriptions of the population or phenomenon of interest.
• Limited depth: Descriptive research design may provide a superficial description of the population or phenomenon of interest. It does not delve into the underlying causes or mechanisms behind the observed behavior or characteristics.
• Limited utility for theory development: Descriptive research design may not be useful for developing theories about the relationship between variables. It only provides a description of the variables themselves.
• Relies on self-report data: Descriptive research design often relies on self-report data, such as surveys or questionnaires. This type of data may be subject to biases, such as social desirability bias or recall bias.

About the author

Muhammad Hassan

Researcher, Academic Writer, Web developer

You may also like

Questionnaire – Definition, Types, and Examples

Case Study – Methods, Examples and Guide

Observational Research – Methods and Guide

Quantitative Research – Methods, Types and...

Qualitative Research Methods

Explanatory Research – Types, Methods, Guide

• school Campus Bookshelves
• menu_book Bookshelves
• perm_media Learning Objects
• login Login
• how_to_reg Request Instructor Account
• hub Instructor Commons
• Download Page (PDF)
• Download Full Book (PDF)
• Periodic Table
• Physics Constants
• Scientific Calculator
• Reference & Cite
• Tools expand_more
• Readability

selected template will load here

This action is not available.

5.8: Descriptive Research

• Last updated
• Save as PDF
• Page ID 59848

Learning Objectives

• Differentiate between descriptive, experimental, and correlational research
• Explain the strengths and weaknesses of case studies, naturalistic observation, and surveys

There are many research methods available to psychologists in their efforts to understand, describe, and explain behavior and the cognitive and biological processes that underlie it. Some methods rely on observational techniques. Other approaches involve interactions between the researcher and the individuals who are being studied—ranging from a series of simple questions to extensive, in-depth interviews—to well-controlled experiments.

The three main categories of psychological research are descriptive, correlational, and experimental research. Research studies that do not test specific relationships between variables are called descriptive, or qualitative, studies . These studies are used to describe general or specific behaviors and attributes that are observed and measured. In the early stages of research it might be difficult to form a hypothesis, especially when there is not any existing literature in the area. In these situations designing an experiment would be premature, as the question of interest is not yet clearly defined as a hypothesis. Often a researcher will begin with a non-experimental approach, such as a descriptive study, to gather more information about the topic before designing an experiment or correlational study to address a specific hypothesis. Descriptive research is distinct from correlational research , in which psychologists formally test whether a relationship exists between two or more variables. Experimental research goes a step further beyond descriptive and correlational research and randomly assigns people to different conditions, using hypothesis testing to make inferences about how these conditions affect behavior. It aims to determine if one variable directly impacts and causes another. Correlational and experimental research both typically use hypothesis testing, whereas descriptive research does not.

Each of these research methods has unique strengths and weaknesses, and each method may only be appropriate for certain types of research questions. For example, studies that rely primarily on observation produce incredible amounts of information, but the ability to apply this information to the larger population is somewhat limited because of small sample sizes. Survey research, on the other hand, allows researchers to easily collect data from relatively large samples. While this allows for results to be generalized to the larger population more easily, the information that can be collected on any given survey is somewhat limited and subject to problems associated with any type of self-reported data. Some researchers conduct archival research by using existing records. While this can be a fairly inexpensive way to collect data that can provide insight into a number of research questions, researchers using this approach have no control on how or what kind of data was collected.

Correlational research can find a relationship between two variables, but the only way a researcher can claim that the relationship between the variables is cause and effect is to perform an experiment. In experimental research, which will be discussed later in the text, there is a tremendous amount of control over variables of interest. While this is a powerful approach, experiments are often conducted in very artificial settings. This calls into question the validity of experimental findings with regard to how they would apply in real-world settings. In addition, many of the questions that psychologists would like to answer cannot be pursued through experimental research because of ethical concerns.

The three main types of descriptive studies are case studies, naturalistic observation, and surveys.

Query \(\PageIndex{1}\)

Query \(\PageIndex{2}\)

Query \(\PageIndex{3}\)

Query \(\PageIndex{4}\)

Case Studies

In 2011, the New York Times published a feature story on Krista and Tatiana Hogan, Canadian twin girls. These particular twins are unique because Krista and Tatiana are conjoined twins, connected at the head. There is evidence that the two girls are connected in a part of the brain called the thalamus, which is a major sensory relay center. Most incoming sensory information is sent through the thalamus before reaching higher regions of the cerebral cortex for processing.

Link to Learning

To learn more about Krista and Tatiana, watch this video about their lives as conjoined twins.

The implications of this potential connection mean that it might be possible for one twin to experience the sensations of the other twin. For instance, if Krista is watching a particularly funny television program, Tatiana might smile or laugh even if she is not watching the program. This particular possibility has piqued the interest of many neuroscientists who seek to understand how the brain uses sensory information.

These twins represent an enormous resource in the study of the brain, and since their condition is very rare, it is likely that as long as their family agrees, scientists will follow these girls very closely throughout their lives to gain as much information as possible (Dominus, 2011).

In observational research, scientists are conducting a clinical or case study when they focus on one person or just a few individuals. Indeed, some scientists spend their entire careers studying just 10–20 individuals. Why would they do this? Obviously, when they focus their attention on a very small number of people, they can gain a tremendous amount of insight into those cases. The richness of information that is collected in clinical or case studies is unmatched by any other single research method. This allows the researcher to have a very deep understanding of the individuals and the particular phenomenon being studied.

If clinical or case studies provide so much information, why are they not more frequent among researchers? As it turns out, the major benefit of this particular approach is also a weakness. As mentioned earlier, this approach is often used when studying individuals who are interesting to researchers because they have a rare characteristic. Therefore, the individuals who serve as the focus of case studies are not like most other people. If scientists ultimately want to explain all behavior, focusing attention on such a special group of people can make it difficult to generalize any observations to the larger population as a whole. Generalizing refers to the ability to apply the findings of a particular research project to larger segments of society. Again, case studies provide enormous amounts of information, but since the cases are so specific, the potential to apply what’s learned to the average person may be very limited.

Query \(\PageIndex{5}\)

Query \(\PageIndex{6}\)

Naturalistic Observation

If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances are that almost everyone in the classroom will raise their hand, but do you think hand washing after every trip to the restroom is really that universal?

This is very similar to the phenomenon mentioned earlier in this module: many individuals do not feel comfortable answering a question honestly. But if we are committed to finding out the facts about hand washing, we have other options available to us.

Suppose we send a classmate into the restroom to actually watch whether everyone washes their hands after using the restroom. Will our observer blend into the restroom environment by wearing a white lab coat, sitting with a clipboard, and staring at the sinks? We want our researcher to be inconspicuous—perhaps standing at one of the sinks pretending to put in contact lenses while secretly recording the relevant information. This type of observational study is called naturalistic observation : observing behavior in its natural setting. To better understand peer exclusion, Suzanne Fanger collaborated with colleagues at the University of Texas to observe the behavior of preschool children on a playground. How did the observers remain inconspicuous over the duration of the study? They equipped a few of the children with wireless microphones (which the children quickly forgot about) and observed while taking notes from a distance. Also, the children in that particular preschool (a “laboratory preschool”) were accustomed to having observers on the playground (Fanger, Frankel, & Hazen, 2012).

It is critical that the observer be as unobtrusive and as inconspicuous as possible: when people know they are being watched, they are less likely to behave naturally. If you have any doubt about this, ask yourself how your driving behavior might differ in two situations: In the first situation, you are driving down a deserted highway during the middle of the day; in the second situation, you are being followed by a police car down the same deserted highway (Figure 1).

It should be pointed out that naturalistic observation is not limited to research involving humans. Indeed, some of the best-known examples of naturalistic observation involve researchers going into the field to observe various kinds of animals in their own environments. As with human studies, the researchers maintain their distance and avoid interfering with the animal subjects so as not to influence their natural behaviors. Scientists have used this technique to study social hierarchies and interactions among animals ranging from ground squirrels to gorillas. The information provided by these studies is invaluable in understanding how those animals organize socially and communicate with one another. The anthropologist Jane Goodall, for example, spent nearly five decades observing the behavior of chimpanzees in Africa (Figure 2). As an illustration of the types of concerns that a researcher might encounter in naturalistic observation, some scientists criticized Goodall for giving the chimps names instead of referring to them by numbers—using names was thought to undermine the emotional detachment required for the objectivity of the study (McKie, 2010).

The greatest benefit of naturalistic observation is the validity, or accuracy, of information collected unobtrusively in a natural setting. Having individuals behave as they normally would in a given situation means that we have a higher degree of ecological validity, or realism, than we might achieve with other research approaches. Therefore, our ability to generalize the findings of the research to real-world situations is enhanced. If done correctly, we need not worry about people or animals modifying their behavior simply because they are being observed. Sometimes, people may assume that reality programs give us a glimpse into authentic human behavior. However, the principle of inconspicuous observation is violated as reality stars are followed by camera crews and are interviewed on camera for personal confessionals. Given that environment, we must doubt how natural and realistic their behaviors are.

The major downside of naturalistic observation is that they are often difficult to set up and control. In our restroom study, what if you stood in the restroom all day prepared to record people’s hand washing behavior and no one came in? Or, what if you have been closely observing a troop of gorillas for weeks only to find that they migrated to a new place while you were sleeping in your tent? The benefit of realistic data comes at a cost. As a researcher you have no control of when (or if) you have behavior to observe. In addition, this type of observational research often requires significant investments of time, money, and a good dose of luck.

Sometimes studies involve structured observation. In these cases, people are observed while engaging in set, specific tasks. An excellent example of structured observation comes from Strange Situation by Mary Ainsworth (you will read more about this in the module on lifespan development). The Strange Situation is a procedure used to evaluate attachment styles that exist between an infant and caregiver. In this scenario, caregivers bring their infants into a room filled with toys. The Strange Situation involves a number of phases, including a stranger coming into the room, the caregiver leaving the room, and the caregiver’s return to the room. The infant’s behavior is closely monitored at each phase, but it is the behavior of the infant upon being reunited with the caregiver that is most telling in terms of characterizing the infant’s attachment style with the caregiver.

Another potential problem in observational research is observer bias . Generally, people who act as observers are closely involved in the research project and may unconsciously skew their observations to fit their research goals or expectations. To protect against this type of bias, researchers should have clear criteria established for the types of behaviors recorded and how those behaviors should be classified. In addition, researchers often compare observations of the same event by multiple observers, in order to test inter-rater reliability : a measure of reliability that assesses the consistency of observations by different observers.

Query \(\PageIndex{7}\)

Query \(\PageIndex{8}\)

Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally (Figure 3). Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.

Surveys allow researchers to gather data from larger samples than may be afforded by other research methods . A sample is a subset of individuals selected from a population , which is the overall group of individuals that the researchers are interested in. Researchers study the sample and seek to generalize their findings to the population.

There is both strength and weakness of the survey in comparison to case studies. By using surveys, we can collect information from a larger sample of people. A larger sample is better able to reflect the actual diversity of the population, thus allowing better generalizability. Therefore, if our sample is sufficiently large and diverse, we can assume that the data we collect from the survey can be generalized to the larger population with more certainty than the information collected through a case study. However, given the greater number of people involved, we are not able to collect the same depth of information on each person that would be collected in a case study.

Another potential weakness of surveys is something we touched on earlier in this module: people don’t always give accurate responses. They may lie, misremember, or answer questions in a way that they think makes them look good. For example, people may report drinking less alcohol than is actually the case.

Any number of research questions can be answered through the use of surveys. One real-world example is the research conducted by Jenkins, Ruppel, Kizer, Yehl, and Griffin (2012) about the backlash against the US Arab-American community following the terrorist attacks of September 11, 2001. Jenkins and colleagues wanted to determine to what extent these negative attitudes toward Arab-Americans still existed nearly a decade after the attacks occurred. In one study, 140 research participants filled out a survey with 10 questions, including questions asking directly about the participant’s overt prejudicial attitudes toward people of various ethnicities. The survey also asked indirect questions about how likely the participant would be to interact with a person of a given ethnicity in a variety of settings (such as, “How likely do you think it is that you would introduce yourself to a person of Arab-American descent?”). The results of the research suggested that participants were unwilling to report prejudicial attitudes toward any ethnic group. However, there were significant differences between their pattern of responses to questions about social interaction with Arab-Americans compared to other ethnic groups: they indicated less willingness for social interaction with Arab-Americans compared to the other ethnic groups. This suggested that the participants harbored subtle forms of prejudice against Arab-Americans, despite their assertions that this was not the case (Jenkins et al., 2012).

Query \(\PageIndex{9}\)

Query \(\PageIndex{10}\)

Query \(\PageIndex{11}\)

Query \(\PageIndex{12}\)

Query \(\PageIndex{13}\)

Think It Over

A friend of yours is working part-time in a local pet store. Your friend has become increasingly interested in how dogs normally communicate and interact with each other, and is thinking of visiting a local veterinary clinic to see how dogs interact in the waiting room. After reading this section, do you think this is the best way to better understand such interactions? Do you have any suggestions that might result in more valid data?

clinical or case study:  observational research study focusing on one or a few people

correlational research:  tests whether a relationship exists between two or more variables

descriptive research:  research studies that do not test specific relationships between variables; they are used to describe general or specific behaviors and attributes that are observed and measured

experimental research:  tests a hypothesis to determine cause and effect relationships

generalize inferring that the results for a sample apply to the larger population

inter-rater reliability:  measure of agreement among observers on how they record and classify a particular event

naturalistic observation:  observation of behavior in its natural setting

observer bias:  when observations may be skewed to align with observer expectations

population:  overall group of individuals that the researchers are interested in

sample:  subset of individuals selected from the larger population

survey:  list of questions to be answered by research participants—given as paper-and-pencil questionnaires, administered electronically, or conducted verbally—allowing researchers to collect data from a large number of people

Licenses and Attributions

CC licensed content, Original

• Modification and adaptation. Provided by : Lumen Learning. License : CC BY-SA: Attribution-ShareAlike
• Approaches to Research. Authored by : OpenStax College. Located at : http://cnx.org/contents/[email protected]:iMyFZJzg@5/Approaches-to-Research . License : CC BY: Attribution . License Terms : Download for free at http://cnx.org/contents/[email protected]
• Descriptive Research. Provided by : Boundless. Located at : https://www.boundless.com/psychology/textbooks/boundless-psychology-textbook/researching-psychology-2/types-of-research-studies-27/descriptive-research-124-12659/ . License : CC BY-SA: Attribution-ShareAlike

• What is descriptive research?

Last updated

5 February 2023

Reviewed by

Cathy Heath

Descriptive research is a common investigatory model used by researchers in various fields, including social sciences, linguistics, and academia.

Read on to understand the characteristics of descriptive research and explore its underlying techniques, processes, and procedures.

Analyze your descriptive research

Dovetail streamlines analysis to help you uncover and share actionable insights

Descriptive research is an exploratory research method. It enables researchers to precisely and methodically describe a population, circumstance, or phenomenon.

As the name suggests, descriptive research describes the characteristics of the group, situation, or phenomenon being studied without manipulating variables or testing hypotheses . This can be reported using surveys , observational studies, and case studies. You can use both quantitative and qualitative methods to compile the data.

Besides making observations and then comparing and analyzing them, descriptive studies often develop knowledge concepts and provide solutions to critical issues. It always aims to answer how the event occurred, when it occurred, where it occurred, and what the problem or phenomenon is.

• Characteristics of descriptive research

The following are some of the characteristics of descriptive research:

Quantitativeness

Descriptive research can be quantitative as it gathers quantifiable data to statistically analyze a population sample. These numbers can show patterns, connections, and trends over time and can be discovered using surveys, polls, and experiments.

Qualitativeness

Descriptive research can also be qualitative. It gives meaning and context to the numbers supplied by quantitative descriptive research .

Researchers can use tools like interviews, focus groups, and ethnographic studies to illustrate why things are what they are and help characterize the research problem. This is because it’s more explanatory than exploratory or experimental research.

Uncontrolled variables

Descriptive research differs from experimental research in that researchers cannot manipulate the variables. They are recognized, scrutinized, and quantified instead. This is one of its most prominent features.

Cross-sectional studies

Descriptive research is a cross-sectional study because it examines several areas of the same group. It involves obtaining data on multiple variables at the personal level during a certain period. It’s helpful when trying to understand a larger community’s habits or preferences.

Carried out in a natural environment

Descriptive studies are usually carried out in the participants’ everyday environment, which allows researchers to avoid influencing responders by collecting data in a natural setting. You can use online surveys or survey questions to collect data or observe.

Basis for further research

You can further dissect descriptive research’s outcomes and use them for different types of investigation. The outcomes also serve as a foundation for subsequent investigations and can guide future studies. For example, you can use the data obtained in descriptive research to help determine future research designs.

• Descriptive research methods

There are three basic approaches for gathering data in descriptive research: observational, case study, and survey.

You can use surveys to gather data in descriptive research. This involves gathering information from many people using a questionnaire and interview .

Surveys remain the dominant research tool for descriptive research design. Researchers can conduct various investigations and collect multiple types of data (quantitative and qualitative) using surveys with diverse designs.

You can conduct surveys over the phone, online, or in person. Your survey might be a brief interview or conversation with a set of prepared questions intended to obtain quick information from the primary source.

Observation

This descriptive research method involves observing and gathering data on a population or phenomena without manipulating variables. It is employed in psychology, market research , and other social science studies to track and understand human behavior.

Observation is an essential component of descriptive research. It entails gathering data and analyzing it to see whether there is a relationship between the two variables in the study. This strategy usually allows for both qualitative and quantitative data analysis.

Case studies

A case study can outline a specific topic’s traits. The topic might be a person, group, event, or organization.

It involves using a subset of a larger group as a sample to characterize the features of that larger group.

You can generalize knowledge gained from studying a case study to benefit a broader audience.

This approach entails carefully examining a particular group, person, or event over time. You can learn something new about the study topic by using a small group to better understand the dynamics of the entire group.

• Types of descriptive research

There are several types of descriptive study. The most well-known include cross-sectional studies, census surveys, sample surveys, case reports, and comparison studies.

Case reports and case series

In the healthcare and medical fields, a case report is used to explain a patient’s circumstances when suffering from an uncommon illness or displaying certain symptoms. Case reports and case series are both collections of related cases. They have aided the advancement of medical knowledge on countless occasions.

The normative component is an addition to the descriptive survey. In the descriptive–normative survey, you compare the study’s results to the norm.

Descriptive survey

This descriptive type of research employs surveys to collect information on various topics. This data aims to determine the degree to which certain conditions may be attained.

You can extrapolate or generalize the information you obtain from sample surveys to the larger group being researched.

Correlative survey

Correlative surveys help establish if there is a positive, negative, or neutral connection between two variables.

Performing census surveys involves gathering relevant data on several aspects of a given population. These units include individuals, families, organizations, objects, characteristics, and properties.

During descriptive research, you gather different degrees of interest over time from a specific population. Cross-sectional studies provide a glimpse of a phenomenon’s prevalence and features in a population. There are no ethical challenges with them and they are quite simple and inexpensive to carry out.

Comparative studies

These surveys compare the two subjects’ conditions or characteristics. The subjects may include research variables, organizations, plans, and people.

Comparison points, assumption of similarities, and criteria of comparison are three important variables that affect how well and accurately comparative studies are conducted.

For instance, descriptive research can help determine how many CEOs hold a bachelor’s degree and what proportion of low-income households receive government help.

• Pros and cons

The primary advantage of descriptive research designs is that researchers can create a reliable and beneficial database for additional study. To conduct any inquiry, you need access to reliable information sources that can give you a firm understanding of a situation.

Quantitative studies are time- and resource-intensive, so knowing the hypotheses viable for testing is crucial. The basic overview of descriptive research provides helpful hints as to which variables are worth quantitatively examining. This is why it’s employed as a precursor to quantitative research designs.

Some experts view this research as untrustworthy and unscientific. However, there is no way to assess the findings because you don’t manipulate any variables statistically.

Cause-and-effect correlations also can’t be established through descriptive investigations. Additionally, observational study findings cannot be replicated, which prevents a review of the findings and their replication.

The absence of statistical and in-depth analysis and the rather superficial character of the investigative procedure are drawbacks of this research approach.

• Descriptive research examples and applications

Several descriptive research examples are emphasized based on their types, purposes, and applications. Research questions often begin with “What is …” These studies help find solutions to practical issues in social science, physical science, and education.

Here are some examples and applications of descriptive research:

Determining consumer perception and behavior

Organizations use descriptive research designs to determine how various demographic groups react to a certain product or service.

For example, a business looking to sell to its target market should research the market’s behavior first. When researching human behavior in response to a cause or event, the researcher pays attention to the traits, actions, and responses before drawing a conclusion.

Scientific classification

Scientific descriptive research enables the classification of organisms and their traits and constituents.

Measuring data trends

A descriptive study design’s statistical capabilities allow researchers to track data trends over time. It’s frequently used to determine the study target’s current circumstances and underlying patterns.

Conduct comparison

Organizations can use a descriptive research approach to learn how various demographics react to a certain product or service. For example, you can study how the target market responds to a competitor’s product and use that information to infer their behavior.

• Bottom line

A descriptive research design is suitable for exploring certain topics and serving as a prelude to larger quantitative investigations. It provides a comprehensive understanding of the “what” of the group or thing you’re investigating.

This research type acts as the cornerstone of other research methodologies . It is distinctive because it can use quantitative and qualitative research approaches at the same time.

What is descriptive research design?

Descriptive research design aims to systematically obtain information to describe a phenomenon, situation, or population. More specifically, it helps answer the what, when, where, and how questions regarding the research problem rather than the why.

How does descriptive research compare to qualitative research?

Despite certain parallels, descriptive research concentrates on describing phenomena, while qualitative research aims to understand people better.

How do you analyze descriptive research data?

Data analysis involves using various methodologies, enabling the researcher to evaluate and provide results regarding validity and reliability.

Get started today

Go from raw data to valuable insights with a flexible research platform

Editor’s picks

Last updated: 21 December 2023

Last updated: 16 December 2023

Last updated: 6 October 2023

Last updated: 25 November 2023

Last updated: 12 May 2023

Last updated: 15 February 2024

Last updated: 11 March 2024

Last updated: 12 December 2023

Last updated: 18 May 2023

Last updated: 6 March 2024

Last updated: 10 April 2023

Last updated: 20 December 2023

Latest articles

Related topics, log in or sign up.

Get started for free

• Descriptive Research Designs: Types, Examples & Methods

One of the components of research is getting enough information about the research problem—the what, how, when and where answers, which is why descriptive research is an important type of research. It is very useful when conducting research whose aim is to identify characteristics, frequencies, trends, correlations, and categories.

This research method takes a problem with little to no relevant information and gives it a befitting description using qualitative and quantitative research method s. Descriptive research aims to accurately describe a research problem.

In the subsequent sections, we will be explaining what descriptive research means, its types, examples, and data collection methods.

What is Descriptive Research?

Descriptive research is a type of research that describes a population, situation, or phenomenon that is being studied. It focuses on answering the how, what, when, and where questions If a research problem, rather than the why.

This is mainly because it is important to have a proper understanding of what a research problem is about before investigating why it exists in the first place. 

For example, an investor considering an investment in the ever-changing Amsterdam housing market needs to understand what the current state of the market is, how it changes (increasing or decreasing), and when it changes (time of the year) before asking for the why. This is where descriptive research comes in.

What Are The Types of Descriptive Research?

Descriptive research is classified into different types according to the kind of approach that is used in conducting descriptive research. The different types of descriptive research are highlighted below:

• Descriptive-survey

Descriptive survey research uses surveys to gather data about varying subjects. This data aims to know the extent to which different conditions can be obtained among these subjects.

For example, a researcher wants to determine the qualification of employed professionals in Maryland. He uses a survey as his research instrument , and each item on the survey related to qualifications is subjected to a Yes/No answer. 

This way, the researcher can describe the qualifications possessed by the employed demographics of this community. 

• Descriptive-normative survey

This is an extension of the descriptive survey, with the addition being the normative element. In the descriptive-normative survey, the results of the study should be compared with the norm.

For example, an organization that wishes to test the skills of its employees by a team may have them take a skills test. The skills tests are the evaluation tool in this case, and the result of this test is compared with the norm of each role.

If the score of the team is one standard deviation above the mean, it is very satisfactory, if within the mean, satisfactory, and one standard deviation below the mean is unsatisfactory.

• Descriptive-status

This is a quantitative description technique that seeks to answer questions about real-life situations. For example, a researcher researching the income of the employees in a company, and the relationship with their performance.

A survey will be carried out to gather enough data about the income of the employees, then their performance will be evaluated and compared to their income. This will help determine whether a higher income means better performance and low income means lower performance or vice versa.

• Descriptive-analysis

The descriptive-analysis method of research describes a subject by further analyzing it, which in this case involves dividing it into 2 parts. For example, the HR personnel of a company that wishes to analyze the job role of each employee of the company may divide the employees into the people that work at the Headquarters in the US and those that work from Oslo, Norway office.

A questionnaire is devised to analyze the job role of employees with similar salaries and who work in similar positions.

• Descriptive classification

This method is employed in biological sciences for the classification of plants and animals. A researcher who wishes to classify the sea animals into different species will collect samples from various search stations, then classify them accordingly.

• Descriptive-comparative

In descriptive-comparative research, the researcher considers 2 variables that are not manipulated, and establish a formal procedure to conclude that one is better than the other. For example, an examination body wants to determine the better method of conducting tests between paper-based and computer-based tests.

A random sample of potential participants of the test may be asked to use the 2 different methods, and factors like failure rates, time factors, and others will be evaluated to arrive at the best method.

• Correlative Survey

Correlative surveys are used to determine whether the relationship between 2 variables is positive, negative, or neutral. That is, if 2 variables say X and Y are directly proportional, inversely proportional or are not related to each other.

Examples of Descriptive Research

There are different examples of descriptive research, that may be highlighted from its types, uses, and applications. However, we will be restricting ourselves to only 3 distinct examples in this article.

• Comparing Student Performance:

An academic institution may wish 2 compare the performance of its junior high school students in English language and Mathematics. This may be used to classify students based on 2 major groups, with one group going ahead to study while courses, while the other study courses in the Arts & Humanities field.

Students who are more proficient in mathematics will be encouraged to go into STEM and vice versa. Institutions may also use this data to identify students’ weak points and work on ways to assist them.

• Scientific Classification

During the major scientific classification of plants, animals, and periodic table elements, the characteristics and components of each subject are evaluated and used to determine how they are classified.

For example, living things may be classified into kingdom Plantae or kingdom animal is depending on their nature. Further classification may group animals into mammals, pieces, vertebrae, invertebrae, etc. 

All these classifications are made a result of descriptive research which describes what they are.

• Human Behavior

When studying human behaviour based on a factor or event, the researcher observes the characteristics, behaviour, and reaction, then use it to conclude. A company willing to sell to its target market needs to first study the behaviour of the market.

This may be done by observing how its target reacts to a competitor’s product, then use it to determine their behaviour.

What are the Characteristics of Descriptive Research?  

The characteristics of descriptive research can be highlighted from its definition, applications, data collection methods, and examples. Some characteristics of descriptive research are:

• Quantitativeness

Descriptive research uses a quantitative research method by collecting quantifiable information to be used for statistical analysis of the population sample. This is very common when dealing with research in the physical sciences.

• Qualitativeness

It can also be carried out using the qualitative research method, to properly describe the research problem. This is because descriptive research is more explanatory than exploratory or experimental.

• Uncontrolled variables

In descriptive research, researchers cannot control the variables like they do in experimental research.

• The basis for further research

The results of descriptive research can be further analyzed and used in other research methods. It can also inform the next line of research, including the research method that should be used.

This is because it provides basic information about the research problem, which may give birth to other questions like why a particular thing is the way it is.

Why Use Descriptive Research Design?  

Descriptive research can be used to investigate the background of a research problem and get the required information needed to carry out further research. It is used in multiple ways by different organizations, and especially when getting the required information about their target audience.

• Define subject characteristics :

It is used to determine the characteristics of the subjects, including their traits, behaviour, opinion, etc. This information may be gathered with the use of surveys, which are shared with the respondents who in this case, are the research subjects.

For example, a survey evaluating the number of hours millennials in a community spends on the internet weekly, will help a service provider make informed business decisions regarding the market potential of the community.

• Measure Data Trends

It helps to measure the changes in data over some time through statistical methods. Consider the case of individuals who want to invest in stock markets, so they evaluate the changes in prices of the available stocks to make a decision investment decision.

Brokerage companies are however the ones who carry out the descriptive research process, while individuals can view the data trends and make decisions.

Descriptive research is also used to compare how different demographics respond to certain variables. For example, an organization may study how people with different income levels react to the launch of a new Apple phone.

This kind of research may take a survey that will help determine which group of individuals are purchasing the new Apple phone. Do the low-income earners also purchase the phone, or only the high-income earners do?

Further research using another technique will explain why low-income earners are purchasing the phone even though they can barely afford it. This will help inform strategies that will lure other low-income earners and increase company sales.

• Validate existing conditions

When you are not sure about the validity of an existing condition, you can use descriptive research to ascertain the underlying patterns of the research object. This is because descriptive research methods make an in-depth analysis of each variable before making conclusions.

• Conducted Overtime

Descriptive research is conducted over some time to ascertain the changes observed at each point in time. The higher the number of times it is conducted, the more authentic the conclusion will be.

What are the Disadvantages of Descriptive Research?  

• Response and Non-response Bias

Respondents may either decide not to respond to questions or give incorrect responses if they feel the questions are too confidential. When researchers use observational methods, respondents may also decide to behave in a particular manner because they feel they are being watched.

• The researcher may decide to influence the result of the research due to personal opinion or bias towards a particular subject. For example, a stockbroker who also has a business of his own may try to lure investors into investing in his own company by manipulating results.
• A case-study or sample taken from a large population is not representative of the whole population.
• Limited scope:The scope of descriptive research is limited to the what of research, with no information on why thereby limiting the scope of the research.

What are the Data Collection Methods in Descriptive Research?  

There are 3 main data collection methods in descriptive research, namely; observational method, case study method, and survey research.

1. Observational Method

The observational method allows researchers to collect data based on their view of the behaviour and characteristics of the respondent, with the respondents themselves not directly having an input. It is often used in market research, psychology, and some other social science research to understand human behaviour.

It is also an important aspect of physical scientific research, with it being one of the most effective methods of conducting descriptive research . This process can be said to be either quantitative or qualitative.

Quantitative observation involved the objective collection of numerical data , whose results can be analyzed using numerical and statistical methods. 

Qualitative observation, on the other hand, involves the monitoring of characteristics and not the measurement of numbers. The researcher makes his observation from a distance, records it, and is used to inform conclusions.

2. Case Study Method

A case study is a sample group (an individual, a group of people, organizations, events, etc.) whose characteristics are used to describe the characteristics of a larger group in which the case study is a subgroup. The information gathered from investigating a case study may be generalized to serve the larger group.

This generalization, may, however, be risky because case studies are not sufficient to make accurate predictions about larger groups. Case studies are a poor case of generalization.

3. Survey Research

This is a very popular data collection method in research designs. In survey research, researchers create a survey or questionnaire and distribute it to respondents who give answers.

Generally, it is used to obtain quick information directly from the primary source and also conducting rigorous quantitative and qualitative research. In some cases, survey research uses a blend of both qualitative and quantitative strategies.

Survey research can be carried out both online and offline using the following methods

• Online Surveys: This is a cheap method of carrying out surveys and getting enough responses. It can be carried out using Formplus, an online survey builder. Formplus has amazing tools and features that will help increase response rates.
• Offline Surveys: This includes paper forms, mobile offline forms , and SMS-based forms.

What Are The Differences Between Descriptive and Correlational Research?  

Before going into the differences between descriptive and correlation research, we need to have a proper understanding of what correlation research is about. Therefore, we will be giving a summary of the correlation research below.

Correlational research is a type of descriptive research, which is used to measure the relationship between 2 variables, with the researcher having no control over them. It aims to find whether there is; positive correlation (both variables change in the same direction), negative correlation (the variables change in the opposite direction), or zero correlation (there is no relationship between the variables).

Correlational research may be used in 2 situations;

(i) when trying to find out if there is a relationship between two variables, and

(ii) when a causal relationship is suspected between two variables, but it is impractical or unethical to conduct experimental research that manipulates one of the variables. 

Below are some of the differences between correlational and descriptive research:

• Definitions :

Descriptive research aims is a type of research that provides an in-depth understanding of the study population, while correlational research is the type of research that measures the relationship between 2 variables. 

• Characteristics :

Descriptive research provides descriptive data explaining what the research subject is about, while correlation research explores the relationship between data and not their description.

• Predictions :

 Predictions cannot be made in descriptive research while correlation research accommodates the possibility of making predictions.

Descriptive Research vs. Causal Research

Descriptive research and causal research are both research methodologies, however, one focuses on a subject’s behaviors while the latter focuses on a relationship’s cause-and-effect. To buttress the above point, descriptive research aims to describe and document the characteristics, behaviors, or phenomena of a particular or specific population or situation. 

It focuses on providing an accurate and detailed account of an already existing state of affairs between variables. Descriptive research answers the questions of “what,” “where,” “when,” and “how” without attempting to establish any causal relationships or explain any underlying factors that might have caused the behavior.

Causal research, on the other hand, seeks to determine cause-and-effect relationships between variables. It aims to point out the factors that influence or cause a particular result or behavior. Causal research involves manipulating variables, controlling conditions or a subgroup, and observing the resulting effects. The primary objective of causal research is to establish a cause-effect relationship and provide insights into why certain phenomena happen the way they do.

Descriptive Research vs. Analytical Research

Descriptive research provides a detailed and comprehensive account of a specific situation or phenomenon. It focuses on describing and summarizing data without making inferences or attempting to explain underlying factors or the cause of the factor. 

It is primarily concerned with providing an accurate and objective representation of the subject of research. While analytical research goes beyond the description of the phenomena and seeks to analyze and interpret data to discover if there are patterns, relationships, or any underlying factors. 

It examines the data critically, applies statistical techniques or other analytical methods, and draws conclusions based on the discovery. Analytical research also aims to explore the relationships between variables and understand the underlying mechanisms or processes involved.

Descriptive Research vs. Exploratory Research

Descriptive research is a research method that focuses on providing a detailed and accurate account of a specific situation, group, or phenomenon. This type of research describes the characteristics, behaviors, or relationships within the given context without looking for an underlying cause. 

Descriptive research typically involves collecting and analyzing quantitative or qualitative data to generate descriptive statistics or narratives. Exploratory research differs from descriptive research because it aims to explore and gain firsthand insights or knowledge into a relatively unexplored or poorly understood topic. 

It focuses on generating ideas, hypotheses, or theories rather than providing definitive answers. Exploratory research is often conducted at the early stages of a research project to gather preliminary information and identify key variables or factors for further investigation. It involves open-ended interviews, observations, or small-scale surveys to gather qualitative data.

Read More – Exploratory Research: What are its Method & Examples?

Descriptive Research vs. Experimental Research

Descriptive research aims to describe and document the characteristics, behaviors, or phenomena of a particular population or situation. It focuses on providing an accurate and detailed account of the existing state of affairs. 

Descriptive research typically involves collecting data through surveys, observations, or existing records and analyzing the data to generate descriptive statistics or narratives. It does not involve manipulating variables or establishing cause-and-effect relationships.

Experimental research, on the other hand, involves manipulating variables and controlling conditions to investigate cause-and-effect relationships. It aims to establish causal relationships by introducing an intervention or treatment and observing the resulting effects. 

Experimental research typically involves randomly assigning participants to different groups, such as control and experimental groups, and measuring the outcomes. It allows researchers to control for confounding variables and draw causal conclusions.

Related – Experimental vs Non-Experimental Research: 15 Key Differences

Descriptive Research vs. Explanatory Research

Descriptive research focuses on providing a detailed and accurate account of a specific situation, group, or phenomenon. It aims to describe the characteristics, behaviors, or relationships within the given context. 

Descriptive research is primarily concerned with providing an objective representation of the subject of study without explaining underlying causes or mechanisms. Explanatory research seeks to explain the relationships between variables and uncover the underlying causes or mechanisms. 

It goes beyond description and aims to understand the reasons or factors that influence a particular outcome or behavior. Explanatory research involves analyzing data, conducting statistical analyses, and developing theories or models to explain the observed relationships.

Descriptive Research vs. Inferential Research

Descriptive research focuses on describing and summarizing data without making inferences or generalizations beyond the specific sample or population being studied. It aims to provide an accurate and objective representation of the subject of study. 

Descriptive research typically involves analyzing data to generate descriptive statistics, such as means, frequencies, or percentages, to describe the characteristics or behaviors observed.

Inferential research, however, involves making inferences or generalizations about a larger population based on a smaller sample. 

It aims to draw conclusions about the population characteristics or relationships by analyzing the sample data. Inferential research uses statistical techniques to estimate population parameters, test hypotheses, and determine the level of confidence or significance in the findings.

Related – Inferential Statistics: Definition, Types + Examples

Conclusion  

The uniqueness of descriptive research partly lies in its ability to explore both quantitative and qualitative research methods. Therefore, when conducting descriptive research, researchers have the opportunity to use a wide variety of techniques that aids the research process.

Descriptive research explores research problems in-depth, beyond the surface level thereby giving a detailed description of the research subject. That way, it can aid further research in the field, including other research methods .

It is also very useful in solving real-life problems in various fields of social science, physical science, and education.

Connect to Formplus, Get Started Now - It's Free!

• descriptive research
• descriptive research method
• example of descriptive research
• types of descriptive research
• busayo.longe

You may also like:

Extrapolation in Statistical Research: Definition, Examples, Types, Applications

In this article we’ll look at the different types and characteristics of extrapolation, plus how it contrasts to interpolation.

Type I vs Type II Errors: Causes, Examples & Prevention

This article will discuss the two different types of errors in hypothesis testing and how you can prevent them from occurring in your research

Cross-Sectional Studies: Types, Pros, Cons & Uses

In this article, we’ll look at what cross-sectional studies are, how it applies to your research and how to use Formplus to collect...

Acceptance Sampling: Meaning, Examples, When to Use

In this post, we will discuss extensively what acceptance sampling is and when it is applied.

Formplus - For Seamless Data Collection

Collect data the right way with a versatile data collection tool. try formplus and transform your work productivity today..

Just one more step to your free trial.

.surveysparrow.com

Already using SurveySparrow?  Login

By clicking on "Get Started", I agree to the Privacy Policy and Terms of Service .

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Don't miss the future of CX at RefineCX USA!  Register Now

Enterprise Survey Software

Enterprise Survey Software to thrive in your business ecosystem

NPS® Software

Turn customers into promoters

Offline Survey

Real-time data collection, on the move. Go internet-independent.

360 Assessment

Conduct omnidirectional employee assessments. Increase productivity, grow together.

Reputation Management

Turn your existing customers into raving promoters by monitoring online reviews.

Ticket Management

Build loyalty and advocacy by delivering personalized support experiences that matter.

Chatbot for Website

Collect feedback smartly from your website visitors with the engaging Chatbot for website.

Swift, easy, secure. Scalable for your organization.

Executive Dashboard

Customer journey map, craft beautiful surveys, share surveys, gain rich insights, recurring surveys, white label surveys, embedded surveys, conversational forms, mobile-first surveys, audience management, smart surveys, video surveys, secure surveys, api, webhooks, integrations, survey themes, accept payments, custom workflows, all features, customer experience, employee experience, product experience, marketing experience, sales experience, hospitality & travel, market research, saas startup programs, wall of love, success stories, sparrowcast, nps® benchmarks, learning centre, apps & integrations, testimonials.

Our surveys come with superpowers ⚡

Blog General

Descriptive Research 101: Definition, Methods and Examples

Parvathi vijayamohan.

8 April 2024

Table Of Contents

• Descriptive Research 101: The Definitive Guide

What is Descriptive Research?

Key characteristics of descriptive research.

• Descriptive Research Methods: The 3 You Need to Know!

Observation

Case studies, 7 types of descriptive research, descriptive research: examples to build your next study, tips to excel at descriptive research.

Imagine you are a detective called to a crime scene. Your job is to study the scene and report whatever you find: whether that’s the half-smoked cigarette on the table or the large “RACHE” written in blood on the wall. That, in a nutshell, is  descriptive research .

Researchers often need to do descriptive research on a problem before they attempt to solve it. So in this guide, we’ll take you through:

• What is descriptive research + characteristics
• Descriptive research methods
• Types of descriptive research
• Descriptive research examples
• Tips to excel at the descriptive method

Click to jump to the section that interests you.

Definition: As its name says, descriptive research  describes  the characteristics of the problem, phenomenon, situation, or group under study.

So the goal of all descriptive studies is to  explore  the background, details, and existing patterns in the problem to fully understand it. In other words, preliminary research.

However, descriptive research can be both  preliminary and conclusive . You can use the data from a descriptive study to make reports and get insights for further planning.

What descriptive research isn’t: Descriptive research finds the  what/when/where  of a problem, not the  why/how .

Because of this, we can’t use the descriptive method to explore cause-and-effect relationships where one variable (like a person’s job role) affects another variable (like their monthly income).

• Answers the “what,” “when,” and “where”  of a research problem. For this reason, it is popularly used in  market research ,  awareness surveys , and  opinion polls .
• Sets the stage  for a research problem. As an early part of the research process, descriptive studies help you dive deeper into the topic.
• Opens the door  for further research. You can use descriptive data as the basis for more profound research, analysis and studies.
• Qualitative and quantitative . It is possible to get a balanced mix of numerical responses and open-ended answers from the descriptive method.
• No control or interference with the variables . The researcher simply observes and reports on them. However, specific research software has filters that allow her to zoom in on one variable.
• Done in natural settings . You can get the best results from descriptive research by talking to people, surveying them, or observing them in a suitable environment. For example, suppose you are a website beta testing an app feature. In that case, descriptive research invites users to try the feature, tracking their behavior and then asking their opinions .
• Can be applied to many research methods and areas. Examples include healthcare, SaaS, psychology, political studies, education, and pop culture.

Descriptive Research Methods: The Top Three You Need to Know!

In short, survey research is a brief interview or conversation with a set of prepared questions about a topic.

So you create a questionnaire, share it, and analyze the data you collect for further action. Learn about the differences between surveys and questionnaires  here .

You can access free survey templates , over 20+ question types, and pass data to 1,500+ applications with survey software, like SurveySparrow . It enables you to create surveys, share them and capture data with very little effort.

Sign up today to launch stunning surveys for free.

Please enter a valid Email ID.

14-Day Free Trial • No Credit Card Required • No Strings Attached

• Surveys can be hyper-local, regional, or global, depending on your objectives.
• Share surveys in-person, offline, via SMS, email, or QR codes – so many options!
• Easy to automate if you want to conduct many surveys over a period.

The observational method is a type of descriptive research in which you, the researcher, observe ongoing behavior.

Now, there are several (non-creepy) ways you can observe someone. In fact, observational research has three main approaches:

• Covert observation: In true spy fashion, the researcher mixes in with the group undetected or observes from a distance.
• Overt observation : The researcher identifies himself as a researcher – “The name’s Bond. J. Bond.” – and explains the purpose of the study.
• Participatory observation : The researcher participates in what he is observing to understand his topic better.
• Observation is one of the most accurate ways to get data on a subject’s behavior in a natural setting.
• You don’t need to rely on people’s willingness to share information.
• Observation is a universal method that can be applied to any area of research.

In the case study method, you do a detailed study of a specific group, person, or event over a period.

This brings us to a frequently asked question: “What’s the difference between case studies and longitudinal studies?”

A case study will go  very in-depth into the subject with one-on-one interviews, observations, and archival research. They are also qualitative, though sometimes they will use numbers and stats.

An example of longitudinal research would be a study of the health of night shift employees vs. general shift employees over a decade. An example of a case study would involve in-depth interviews with Casey, an assistant director of nursing who’s handled the night shift at the hospital for ten years now.

• Due to the focus on a few people, case studies can give you a tremendous amount of information.
• Because of the time and effort involved, a case study engages both researchers and participants.
• Case studies are helpful for ethically investigating unusual, complex, or challenging subjects. An example would be a study of the habits of long-term cocaine users.

1. Case Study: Airbnb’s Growth Strategy

In an excellent case study, Tam Al Saad, Principal Consultant, Strategy + Growth at Webprofits, deep dives into how Airbnb attracted and retained 150 million users .

“What Airbnb offers isn’t a cheap place to sleep when you’re on holiday; it’s the opportunity to experience your destination as a local would. It’s the chance to meet the locals, experience the markets, and find non-touristy places.

Sure, you can visit the Louvre, see Buckingham Palace, and climb the Empire State Building, but you can do it as if it were your hometown while staying in a place that has character and feels like a home.” – Tam al Saad, Principal Consultant, Strategy + Growth at Webprofits

2. Observation – Better Tech Experiences for the Elderly

We often think that our elders are so hopeless with technology. But we’re not getting any younger either, and tech is changing at a hair trigger! This article by Annemieke Hendricks shares a wonderful example where researchers compare the levels of technological familiarity between age groups and how that influences usage.

“It is generally assumed that older adults have difficulty using modern electronic devices, such as mobile telephones or computers. Because this age group is growing in most countries, changing products and processes to adapt to their needs is increasingly more important. “ – Annemieke Hendricks, Marketing Communication Specialist, Noldus

3. Surveys – Decoding Sleep with SurveySparrow

SRI International (formerly Stanford Research Institute) – an independent, non-profit research center – wanted to investigate the impact of stress on an adolescent’s sleep. To get those insights, two actions were essential: tracking sleep patterns through wearable devices and sending surveys at a pre-set time –  the pre-sleep period.

“With SurveySparrow’s recurring surveys feature, SRI was able to share engaging surveys with their participants exactly at the time they wanted and at the frequency they preferred.”

Read more about this project : How SRI International decoded sleep patterns with SurveySparrow

1: Answer the six Ws –

• Who should we consider?
• What information do we need?
• When should we collect the information?
• Where should we collect the information?
• Why are we obtaining the information?
• Way to collect the information

#2: Introduce and explain your methodological approach

#3: Describe your methods of data collection and/or selection.

#4: Describe your methods of analysis.

#5: Explain the reasoning behind your choices.

#6: Collect data.

#7: Analyze the data. Use software to speed up the process and reduce overthinking and human error.

#8: Report your conclusions and how you drew the results.

Wrapping Up

That’s all, folks!

Growth Marketer at SurveySparrow

Fledgling growth marketer. Cloud watcher. Aunty to a naughty beagle.

You Might Also Like

What is customer intelligence (ci) & why it is important, how to create a product roadmap: an essential guide to successful product planning, t-shirt order form: guide to creating custom forms, with free template and examples.

Leave us your email, we wont spam. Promise!

Start your free trial today

No Credit Card Required. 14-Day Free Trial

Request a Demo

Want to learn more about SurveySparrow? We'll be in touch soon!

Scale up your descriptive research with the best survey software

Build surveys that actually work. give surveysparrow a free try today.

14-Day Free Trial • No Credit card required • 40% more completion rate

Hi there, we use cookies to offer you a better browsing experience and to analyze site traffic. By continuing to use our website, you consent to the use of these cookies. Learn More

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Methodology
• Descriptive Research Design | Definition, Methods & Examples

Descriptive Research Design | Definition, Methods & Examples

Published on 5 May 2022 by Shona McCombes . Revised on 10 October 2022.

Descriptive research aims to accurately and systematically describe a population, situation or phenomenon. It can answer what , where , when , and how   questions , but not why questions.

A descriptive research design can use a wide variety of research methods  to investigate one or more variables . Unlike in experimental research , the researcher does not control or manipulate any of the variables, but only observes and measures them.

Table of contents

When to use a descriptive research design, descriptive research methods.

Descriptive research is an appropriate choice when the research aim is to identify characteristics, frequencies, trends, and categories.

It is useful when not much is known yet about the topic or problem. Before you can research why something happens, you need to understand how, when, and where it happens.

• How has the London housing market changed over the past 20 years?
• Do customers of company X prefer product Y or product Z?
• What are the main genetic, behavioural, and morphological differences between European wildcats and domestic cats?
• What are the most popular online news sources among under-18s?
• How prevalent is disease A in population B?

Prevent plagiarism, run a free check.

Descriptive research is usually defined as a type of quantitative research , though qualitative research can also be used for descriptive purposes. The research design should be carefully developed to ensure that the results are valid and reliable .

Survey research allows you to gather large volumes of data that can be analysed for frequencies, averages, and patterns. Common uses of surveys include:

• Describing the demographics of a country or region
• Gauging public opinion on political and social topics
• Evaluating satisfaction with a company’s products or an organisation’s services

Observations

Observations allow you to gather data on behaviours and phenomena without having to rely on the honesty and accuracy of respondents. This method is often used by psychological, social, and market researchers to understand how people act in real-life situations.

Observation of physical entities and phenomena is also an important part of research in the natural sciences. Before you can develop testable hypotheses , models, or theories, it’s necessary to observe and systematically describe the subject under investigation.

Case studies

A case study can be used to describe the characteristics of a specific subject (such as a person, group, event, or organisation). Instead of gathering a large volume of data to identify patterns across time or location, case studies gather detailed data to identify the characteristics of a narrowly defined subject.

Rather than aiming to describe generalisable facts, case studies often focus on unusual or interesting cases that challenge assumptions, add complexity, or reveal something new about a research problem .

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

McCombes, S. (2022, October 10). Descriptive Research Design | Definition, Methods & Examples. Scribbr. Retrieved 22 April 2024, from https://www.scribbr.co.uk/research-methods/descriptive-research-design/

Is this article helpful?

Shona McCombes

Other students also liked, a quick guide to experimental design | 5 steps & examples, correlational research | guide, design & examples, qualitative vs quantitative research | examples & methods.

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

Chapter 3. Psychological Science

3.2 Psychologists Use Descriptive, Correlational, and Experimental Research Designs to Understand Behaviour

Learning objectives.

• Differentiate the goals of descriptive, correlational, and experimental research designs and explain the advantages and disadvantages of each.
• Explain the goals of descriptive research and the statistical techniques used to interpret it.
• Summarize the uses of correlational research and describe why correlational research cannot be used to infer causality.
• Review the procedures of experimental research and explain how it can be used to draw causal inferences.

Psychologists agree that if their ideas and theories about human behaviour are to be taken seriously, they must be backed up by data. However, the research of different psychologists is designed with different goals in mind, and the different goals require different approaches. These varying approaches, summarized in Table 3.2, are known as research designs . A research design  is the specific method a researcher uses to collect, analyze, and interpret data . Psychologists use three major types of research designs in their research, and each provides an essential avenue for scientific investigation. Descriptive research  is research designed to provide a snapshot of the current state of affairs . Correlational research  is research designed to discover relationships among variables and to allow the prediction of future events from present knowledge . Experimental research  is research in which initial equivalence among research participants in more than one group is created, followed by a manipulation of a given experience for these groups and a measurement of the influence of the manipulation . Each of the three research designs varies according to its strengths and limitations, and it is important to understand how each differs.

Descriptive Research: Assessing the Current State of Affairs

Descriptive research is designed to create a snapshot of the current thoughts, feelings, or behaviour of individuals. This section reviews three types of descriptive research : case studies , surveys , and naturalistic observation (Figure 3.4).

Sometimes the data in a descriptive research project are based on only a small set of individuals, often only one person or a single small group. These research designs are known as case studies — descriptive records of one or more individual’s experiences and behaviour . Sometimes case studies involve ordinary individuals, as when developmental psychologist Jean Piaget used his observation of his own children to develop his stage theory of cognitive development. More frequently, case studies are conducted on individuals who have unusual or abnormal experiences or characteristics or who find themselves in particularly difficult or stressful situations. The assumption is that by carefully studying individuals who are socially marginal, who are experiencing unusual situations, or who are going through a difficult phase in their lives, we can learn something about human nature.

Sigmund Freud was a master of using the psychological difficulties of individuals to draw conclusions about basic psychological processes. Freud wrote case studies of some of his most interesting patients and used these careful examinations to develop his important theories of personality. One classic example is Freud’s description of “Little Hans,” a child whose fear of horses the psychoanalyst interpreted in terms of repressed sexual impulses and the Oedipus complex (Freud, 1909/1964).

Another well-known case study is Phineas Gage, a man whose thoughts and emotions were extensively studied by cognitive psychologists after a railroad spike was blasted through his skull in an accident. Although there are questions about the interpretation of this case study (Kotowicz, 2007), it did provide early evidence that the brain’s frontal lobe is involved in emotion and morality (Damasio et al., 2005). An interesting example of a case study in clinical psychology is described by Rokeach (1964), who investigated in detail the beliefs of and interactions among three patients with schizophrenia, all of whom were convinced they were Jesus Christ.

In other cases the data from descriptive research projects come in the form of a survey — a measure administered through either an interview or a written questionnaire to get a picture of the beliefs or behaviours of a sample of people of interest . The people chosen to participate in the research (known as the sample) are selected to be representative of all the people that the researcher wishes to know about (the population). In election polls, for instance, a sample is taken from the population of all “likely voters” in the upcoming elections.

The results of surveys may sometimes be rather mundane, such as “Nine out of 10 doctors prefer Tymenocin” or “The median income in the city of Hamilton is $46,712.” Yet other times (particularly in discussions of social behaviour), the results can be shocking: “More than 40,000 people are killed by gunfire in the United States every year” or “More than 60% of women between the ages of 50 and 60 suffer from depression.” Descriptive research is frequently used by psychologists to get an estimate of the prevalence (or incidence ) of psychological disorders.

A final type of descriptive research — known as naturalistic observation — is research based on the observation of everyday events . For instance, a developmental psychologist who watches children on a playground and describes what they say to each other while they play is conducting descriptive research, as is a biopsychologist who observes animals in their natural habitats. One example of observational research involves a systematic procedure known as the strange situation , used to get a picture of how adults and young children interact. The data that are collected in the strange situation are systematically coded in a coding sheet such as that shown in Table 3.3.

The results of descriptive research projects are analyzed using descriptive statistics — numbers that summarize the distribution of scores on a measured variable . Most variables have distributions similar to that shown in Figure 3.5 where most of the scores are located near the centre of the distribution, and the distribution is symmetrical and bell-shaped. A data distribution that is shaped like a bell is known as a normal distribution .

A distribution can be described in terms of its central tendency — that is, the point in the distribution around which the data are centred — and its dispersion, or spread . The arithmetic average, or arithmetic mean , symbolized by the letter M , is the most commonly used measure of central tendency . It is computed by calculating the sum of all the scores of the variable and dividing this sum by the number of participants in the distribution (denoted by the letter N ). In the data presented in Figure 3.5 the mean height of the students is 67.12 inches (170.5 cm). The sample mean is usually indicated by the letter M .

In some cases, however, the data distribution is not symmetrical. This occurs when there are one or more extreme scores (known as outliers ) at one end of the distribution. Consider, for instance, the variable of family income (see Figure 3.6), which includes an outlier (a value of $3,800,000). In this case the mean is not a good measure of central tendency. Although it appears from Figure 3.6 that the central tendency of the family income variable should be around $70,000, the mean family income is actually $223,960. The single very extreme income has a disproportionate impact on the mean, resulting in a value that does not well represent the central tendency.

The median is used as an alternative measure of central tendency when distributions are not symmetrical. The median  is the score in the center of the distribution, meaning that 50% of the scores are greater than the median and 50% of the scores are less than the median . In our case, the median household income ($73,000) is a much better indication of central tendency than is the mean household income ($223,960).

A final measure of central tendency, known as the mode , represents the value that occurs most frequently in the distribution . You can see from Figure 3.6 that the mode for the family income variable is $93,000 (it occurs four times).

In addition to summarizing the central tendency of a distribution, descriptive statistics convey information about how the scores of the variable are spread around the central tendency. Dispersion refers to the extent to which the scores are all tightly clustered around the central tendency , as seen in Figure 3.7.

Or they may be more spread out away from it, as seen in Figure 3.8.

One simple measure of dispersion is to find the largest (the maximum ) and the smallest (the minimum ) observed values of the variable and to compute the range of the variable as the maximum observed score minus the minimum observed score. You can check that the range of the height variable in Figure 3.5 is 72 – 62 = 10. The standard deviation , symbolized as s , is the most commonly used measure of dispersion . Distributions with a larger standard deviation have more spread. The standard deviation of the height variable is s = 2.74, and the standard deviation of the family income variable is s = $745,337.

An advantage of descriptive research is that it attempts to capture the complexity of everyday behaviour. Case studies provide detailed information about a single person or a small group of people, surveys capture the thoughts or reported behaviours of a large population of people, and naturalistic observation objectively records the behaviour of people or animals as it occurs naturally. Thus descriptive research is used to provide a relatively complete understanding of what is currently happening.

Despite these advantages, descriptive research has a distinct disadvantage in that, although it allows us to get an idea of what is currently happening, it is usually limited to static pictures. Although descriptions of particular experiences may be interesting, they are not always transferable to other individuals in other situations, nor do they tell us exactly why specific behaviours or events occurred. For instance, descriptions of individuals who have suffered a stressful event, such as a war or an earthquake, can be used to understand the individuals’ reactions to the event but cannot tell us anything about the long-term effects of the stress. And because there is no comparison group that did not experience the stressful situation, we cannot know what these individuals would be like if they hadn’t had the stressful experience.

Correlational Research: Seeking Relationships among Variables

In contrast to descriptive research, which is designed primarily to provide static pictures, correlational research involves the measurement of two or more relevant variables and an assessment of the relationship between or among those variables. For instance, the variables of height and weight are systematically related (correlated) because taller people generally weigh more than shorter people. In the same way, study time and memory errors are also related, because the more time a person is given to study a list of words, the fewer errors he or she will make. When there are two variables in the research design, one of them is called the predictor variable and the other the outcome variable . The research design can be visualized as shown in Figure 3.9, where the curved arrow represents the expected correlation between these two variables.

One way of organizing the data from a correlational study with two variables is to graph the values of each of the measured variables using a scatter plot . As you can see in Figure 3.10 a scatter plot  is a visual image of the relationship between two variables . A point is plotted for each individual at the intersection of his or her scores for the two variables. When the association between the variables on the scatter plot can be easily approximated with a straight line , as in parts (a) and (b) of Figure 3.10 the variables are said to have a linear relationship .

When the straight line indicates that individuals who have above-average values for one variable also tend to have above-average values for the other variable , as in part (a), the relationship is said to be positive linear . Examples of positive linear relationships include those between height and weight, between education and income, and between age and mathematical abilities in children. In each case, people who score higher on one of the variables also tend to score higher on the other variable. Negative linear relationships , in contrast, as shown in part (b), occur when above-average values for one variable tend to be associated with below-average values for the other variable. Examples of negative linear relationships include those between the age of a child and the number of diapers the child uses, and between practice on and errors made on a learning task. In these cases, people who score higher on one of the variables tend to score lower on the other variable.

Relationships between variables that cannot be described with a straight line are known as nonlinear relationships . Part (c) of Figure 3.10 shows a common pattern in which the distribution of the points is essentially random. In this case there is no relationship at all between the two variables, and they are said to be independent . Parts (d) and (e) of Figure 3.10 show patterns of association in which, although there is an association, the points are not well described by a single straight line. For instance, part (d) shows the type of relationship that frequently occurs between anxiety and performance. Increases in anxiety from low to moderate levels are associated with performance increases, whereas increases in anxiety from moderate to high levels are associated with decreases in performance. Relationships that change in direction and thus are not described by a single straight line are called curvilinear relationships .

The most common statistical measure of the strength of linear relationships among variables is the Pearson correlation coefficient , which is symbolized by the letter r . The value of the correlation coefficient ranges from r = –1.00 to r = +1.00. The direction of the linear relationship is indicated by the sign of the correlation coefficient. Positive values of r (such as r = .54 or r = .67) indicate that the relationship is positive linear (i.e., the pattern of the dots on the scatter plot runs from the lower left to the upper right), whereas negative values of r (such as r = –.30 or r = –.72) indicate negative linear relationships (i.e., the dots run from the upper left to the lower right). The strength of the linear relationship is indexed by the distance of the correlation coefficient from zero (its absolute value). For instance, r = –.54 is a stronger relationship than r = .30, and r = .72 is a stronger relationship than r = –.57. Because the Pearson correlation coefficient only measures linear relationships, variables that have curvilinear relationships are not well described by r , and the observed correlation will be close to zero.

It is also possible to study relationships among more than two measures at the same time. A research design in which more than one predictor variable is used to predict a single outcome variable is analyzed through multiple regression (Aiken & West, 1991).  Multiple regression  is a statistical technique, based on correlation coefficients among variables, that allows predicting a single outcome variable from more than one predictor variable . For instance, Figure 3.11 shows a multiple regression analysis in which three predictor variables (Salary, job satisfaction, and years employed) are used to predict a single outcome (job performance). The use of multiple regression analysis shows an important advantage of correlational research designs — they can be used to make predictions about a person’s likely score on an outcome variable (e.g., job performance) based on knowledge of other variables.

An important limitation of correlational research designs is that they cannot be used to draw conclusions about the causal relationships among the measured variables. Consider, for instance, a researcher who has hypothesized that viewing violent behaviour will cause increased aggressive play in children. He has collected, from a sample of Grade 4 children, a measure of how many violent television shows each child views during the week, as well as a measure of how aggressively each child plays on the school playground. From his collected data, the researcher discovers a positive correlation between the two measured variables.

Although this positive correlation appears to support the researcher’s hypothesis, it cannot be taken to indicate that viewing violent television causes aggressive behaviour. Although the researcher is tempted to assume that viewing violent television causes aggressive play, there are other possibilities. One alternative possibility is that the causal direction is exactly opposite from what has been hypothesized. Perhaps children who have behaved aggressively at school develop residual excitement that leads them to want to watch violent television shows at home (Figure 3.13):

Although this possibility may seem less likely, there is no way to rule out the possibility of such reverse causation on the basis of this observed correlation. It is also possible that both causal directions are operating and that the two variables cause each other (Figure 3.14).

Still another possible explanation for the observed correlation is that it has been produced by the presence of a common-causal variable (also known as a third variable ). A common-causal variable  is a variable that is not part of the research hypothesis but that causes both the predictor and the outcome variable and thus produces the observed correlation between them . In our example, a potential common-causal variable is the discipline style of the children’s parents. Parents who use a harsh and punitive discipline style may produce children who like to watch violent television and who also behave aggressively in comparison to children whose parents use less harsh discipline (Figure 3.15)

In this case, television viewing and aggressive play would be positively correlated (as indicated by the curved arrow between them), even though neither one caused the other but they were both caused by the discipline style of the parents (the straight arrows). When the predictor and outcome variables are both caused by a common-causal variable, the observed relationship between them is said to be spurious . A spurious relationship  is a relationship between two variables in which a common-causal variable produces and “explains away” the relationship . If effects of the common-causal variable were taken away, or controlled for, the relationship between the predictor and outcome variables would disappear. In the example, the relationship between aggression and television viewing might be spurious because by controlling for the effect of the parents’ disciplining style, the relationship between television viewing and aggressive behaviour might go away.

Common-causal variables in correlational research designs can be thought of as mystery variables because, as they have not been measured, their presence and identity are usually unknown to the researcher. Since it is not possible to measure every variable that could cause both the predictor and outcome variables, the existence of an unknown common-causal variable is always a possibility. For this reason, we are left with the basic limitation of correlational research: correlation does not demonstrate causation. It is important that when you read about correlational research projects, you keep in mind the possibility of spurious relationships, and be sure to interpret the findings appropriately. Although correlational research is sometimes reported as demonstrating causality without any mention being made of the possibility of reverse causation or common-causal variables, informed consumers of research, like you, are aware of these interpretational problems.

In sum, correlational research designs have both strengths and limitations. One strength is that they can be used when experimental research is not possible because the predictor variables cannot be manipulated. Correlational designs also have the advantage of allowing the researcher to study behaviour as it occurs in everyday life. And we can also use correlational designs to make predictions — for instance, to predict from the scores on their battery of tests the success of job trainees during a training session. But we cannot use such correlational information to determine whether the training caused better job performance. For that, researchers rely on experiments.

Experimental Research: Understanding the Causes of Behaviour

The goal of experimental research design is to provide more definitive conclusions about the causal relationships among the variables in the research hypothesis than is available from correlational designs. In an experimental research design, the variables of interest are called the independent variable (or variables ) and the dependent variable . The independent variable  in an experiment is the causing variable that is created (manipulated) by the experimenter . The dependent variable  in an experiment is a measured variable that is expected to be influenced by the experimental manipulation . The research hypothesis suggests that the manipulated independent variable or variables will cause changes in the measured dependent variables. We can diagram the research hypothesis by using an arrow that points in one direction. This demonstrates the expected direction of causality (Figure 3.16):

Research Focus: Video Games and Aggression

Consider an experiment conducted by Anderson and Dill (2000). The study was designed to test the hypothesis that viewing violent video games would increase aggressive behaviour. In this research, male and female undergraduates from Iowa State University were given a chance to play with either a violent video game (Wolfenstein 3D) or a nonviolent video game (Myst). During the experimental session, the participants played their assigned video games for 15 minutes. Then, after the play, each participant played a competitive game with an opponent in which the participant could deliver blasts of white noise through the earphones of the opponent. The operational definition of the dependent variable (aggressive behaviour) was the level and duration of noise delivered to the opponent. The design of the experiment is shown in Figure 3.17

Two advantages of the experimental research design are (a) the assurance that the independent variable (also known as the experimental manipulation ) occurs prior to the measured dependent variable, and (b) the creation of initial equivalence between the conditions of the experiment (in this case by using random assignment to conditions).

Experimental designs have two very nice features. For one, they guarantee that the independent variable occurs prior to the measurement of the dependent variable. This eliminates the possibility of reverse causation. Second, the influence of common-causal variables is controlled, and thus eliminated, by creating initial equivalence among the participants in each of the experimental conditions before the manipulation occurs.

The most common method of creating equivalence among the experimental conditions is through random assignment to conditions, a procedure in which the condition that each participant is assigned to is determined through a random process, such as drawing numbers out of an envelope or using a random number table . Anderson and Dill first randomly assigned about 100 participants to each of their two groups (Group A and Group B). Because they used random assignment to conditions, they could be confident that, before the experimental manipulation occurred, the students in Group A were, on average, equivalent to the students in Group B on every possible variable, including variables that are likely to be related to aggression, such as parental discipline style, peer relationships, hormone levels, diet — and in fact everything else.

Then, after they had created initial equivalence, Anderson and Dill created the experimental manipulation — they had the participants in Group A play the violent game and the participants in Group B play the nonviolent game. Then they compared the dependent variable (the white noise blasts) between the two groups, finding that the students who had viewed the violent video game gave significantly longer noise blasts than did the students who had played the nonviolent game.

Anderson and Dill had from the outset created initial equivalence between the groups. This initial equivalence allowed them to observe differences in the white noise levels between the two groups after the experimental manipulation, leading to the conclusion that it was the independent variable (and not some other variable) that caused these differences. The idea is that the only thing that was different between the students in the two groups was the video game they had played.

Despite the advantage of determining causation, experiments do have limitations. One is that they are often conducted in laboratory situations rather than in the everyday lives of people. Therefore, we do not know whether results that we find in a laboratory setting will necessarily hold up in everyday life. Second, and more important, is that some of the most interesting and key social variables cannot be experimentally manipulated. If we want to study the influence of the size of a mob on the destructiveness of its behaviour, or to compare the personality characteristics of people who join suicide cults with those of people who do not join such cults, these relationships must be assessed using correlational designs, because it is simply not possible to experimentally manipulate these variables.

Key Takeaways

• Descriptive, correlational, and experimental research designs are used to collect and analyze data.
• Descriptive designs include case studies, surveys, and naturalistic observation. The goal of these designs is to get a picture of the current thoughts, feelings, or behaviours in a given group of people. Descriptive research is summarized using descriptive statistics.
• Correlational research designs measure two or more relevant variables and assess a relationship between or among them. The variables may be presented on a scatter plot to visually show the relationships. The Pearson Correlation Coefficient ( r ) is a measure of the strength of linear relationship between two variables.
• Common-causal variables may cause both the predictor and outcome variable in a correlational design, producing a spurious relationship. The possibility of common-causal variables makes it impossible to draw causal conclusions from correlational research designs.
• Experimental research involves the manipulation of an independent variable and the measurement of a dependent variable. Random assignment to conditions is normally used to create initial equivalence between the groups, allowing researchers to draw causal conclusions.

Exercises and Critical Thinking

• There is a negative correlation between the row that a student sits in in a large class (when the rows are numbered from front to back) and his or her final grade in the class. Do you think this represents a causal relationship or a spurious relationship, and why?
• Think of two variables (other than those mentioned in this book) that are likely to be correlated, but in which the correlation is probably spurious. What is the likely common-causal variable that is producing the relationship?
• Imagine a researcher wants to test the hypothesis that participating in psychotherapy will cause a decrease in reported anxiety. Describe the type of research design the investigator might use to draw this conclusion. What would be the independent and dependent variables in the research?

Image Attributions

Figure 3.4: “ Reading newspaper ” by Alaskan Dude (http://commons.wikimedia.org/wiki/File:Reading_newspaper.jpg) is licensed under CC BY 2.0

Aiken, L., & West, S. (1991).  Multiple regression: Testing and interpreting interactions . Newbury Park, CA: Sage.

Ainsworth, M. S., Blehar, M. C., Waters, E., & Wall, S. (1978).  Patterns of attachment: A psychological study of the strange situation . Hillsdale, NJ: Lawrence Erlbaum Associates.

Anderson, C. A., & Dill, K. E. (2000). Video games and aggressive thoughts, feelings, and behavior in the laboratory and in life.  Journal of Personality and Social Psychology, 78 (4), 772–790.

Damasio, H., Grabowski, T., Frank, R., Galaburda, A. M., Damasio, A. R., Cacioppo, J. T., & Berntson, G. G. (2005). The return of Phineas Gage: Clues about the brain from the skull of a famous patient. In  Social neuroscience: Key readings.  (pp. 21–28). New York, NY: Psychology Press.

Freud, S. (1909/1964). Analysis of phobia in a five-year-old boy. In E. A. Southwell & M. Merbaum (Eds.),  Personality: Readings in theory and research  (pp. 3–32). Belmont, CA: Wadsworth. (Original work published 1909).

Kotowicz, Z. (2007). The strange case of Phineas Gage.  History of the Human Sciences, 20 (1), 115–131.

Rokeach, M. (1964).  The three Christs of Ypsilanti: A psychological study . New York, NY: Knopf.

Stangor, C. (2011). Research methods for the behavioural sciences (4th ed.). Mountain View, CA: Cengage.

Long Descriptions

Figure 3.6 long description: There are 25 families. 24 families have an income between $44,000 and $111,000 and one family has an income of $3,800,000. The mean income is $223,960 while the median income is $73,000. [Return to Figure 3.6]

Figure 3.10 long description: Types of scatter plots.

• Positive linear, r=positive .82. The plots on the graph form a rough line that runs from lower left to upper right.
• Negative linear, r=negative .70. The plots on the graph form a rough line that runs from upper left to lower right.
• Independent, r=0.00. The plots on the graph are spread out around the centre.
• Curvilinear, r=0.00. The plots of the graph form a rough line that goes up and then down like a hill.
• Curvilinear, r=0.00. The plots on the graph for a rough line that goes down and then up like a ditch.

[Return to Figure 3.10]

Introduction to Psychology - 1st Canadian Edition Copyright © 2014 by Jennifer Walinga and Charles Stangor is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

• Bipolar Disorder
• Therapy Center
• When To See a Therapist
• Types of Therapy
• Best Online Therapy
• Best Couples Therapy
• Best Family Therapy
• Managing Stress
• Sleep and Dreaming
• Understanding Emotions
• Self-Improvement
• Healthy Relationships
• Student Resources
• Personality Types
• Guided Meditations
• Verywell Mind Insights
• 2023 Verywell Mind 25
• Mental Health in the Classroom
• Editorial Process
• Meet Our Review Board
• Crisis Support

Introduction to Research Methods in Psychology

Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

Emily is a board-certified science editor who has worked with top digital publishing brands like Voices for Biodiversity, Study.com, GoodTherapy, Vox, and Verywell.

There are several different research methods in psychology , each of which can help researchers learn more about the way people think, feel, and behave. If you're a psychology student or just want to know the types of research in psychology, here are the main ones as well as how they work.

Three Main Types of Research in Psychology

stevecoleimages/Getty Images

Psychology research can usually be classified as one of three major types.

1. Causal or Experimental Research

When most people think of scientific experimentation, research on cause and effect is most often brought to mind. Experiments on causal relationships investigate the effect of one or more variables on one or more outcome variables. This type of research also determines if one variable causes another variable to occur or change.

An example of this type of research in psychology would be changing the length of a specific mental health treatment and measuring the effect on study participants.

2. Descriptive Research

Descriptive research seeks to depict what already exists in a group or population. Three types of psychology research utilizing this method are:

• Case studies
• Observational studies

An example of this psychology research method would be an opinion poll to determine which presidential candidate people plan to vote for in the next election. Descriptive studies don't try to measure the effect of a variable; they seek only to describe it.

3. Relational or Correlational Research

A study that investigates the connection between two or more variables is considered relational research. The variables compared are generally already present in the group or population.

For example, a study that looks at the proportion of males and females that would purchase either a classical CD or a jazz CD would be studying the relationship between gender and music preference.

Theory vs. Hypothesis in Psychology Research

People often confuse the terms theory and hypothesis or are not quite sure of the distinctions between the two concepts. If you're a psychology student, it's essential to understand what each term means, how they differ, and how they're used in psychology research.

A theory is a well-established principle that has been developed to explain some aspect of the natural world. A theory arises from repeated observation and testing and incorporates facts, laws, predictions, and tested hypotheses that are widely accepted.

A hypothesis is a specific, testable prediction about what you expect to happen in your study. For example, an experiment designed to look at the relationship between study habits and test anxiety might have a hypothesis that states, "We predict that students with better study habits will suffer less test anxiety." Unless your study is exploratory in nature, your hypothesis should always explain what you expect to happen during the course of your experiment or research.

While the terms are sometimes used interchangeably in everyday use, the difference between a theory and a hypothesis is important when studying experimental design.

Some other important distinctions to note include:

• A theory predicts events in general terms, while a hypothesis makes a specific prediction about a specified set of circumstances.
• A theory has been extensively tested and is generally accepted, while a hypothesis is a speculative guess that has yet to be tested.

The Effect of Time on Research Methods in Psychology

There are two types of time dimensions that can be used in designing a research study:

• Cross-sectional research takes place at a single point in time. All tests, measures, or variables are administered to participants on one occasion. This type of research seeks to gather data on present conditions instead of looking at the effects of a variable over a period of time.
• Longitudinal research is a study that takes place over a period of time. Data is first collected at the beginning of the study, and may then be gathered repeatedly throughout the length of the study. Some longitudinal studies may occur over a short period of time, such as a few days, while others may take place over a period of months, years, or even decades.

The effects of aging are often investigated using longitudinal research.

Causal Relationships Between Psychology Research Variables

What do we mean when we talk about a “relationship” between variables? In psychological research, we're referring to a connection between two or more factors that we can measure or systematically vary.

One of the most important distinctions to make when discussing the relationship between variables is the meaning of causation.

A causal relationship is when one variable causes a change in another variable. These types of relationships are investigated by experimental research to determine if changes in one variable actually result in changes in another variable.

Correlational Relationships Between Psychology Research Variables

A correlation is the measurement of the relationship between two variables. These variables already occur in the group or population and are not controlled by the experimenter.

• A positive correlation is a direct relationship where, as the amount of one variable increases, the amount of a second variable also increases.
• In a negative correlation , as the amount of one variable goes up, the levels of another variable go down.

In both types of correlation, there is no evidence or proof that changes in one variable cause changes in the other variable. A correlation simply indicates that there is a relationship between the two variables.

The most important concept is that correlation does not equal causation. Many popular media sources make the mistake of assuming that simply because two variables are related, a causal relationship exists.

Psychologists use descriptive, correlational, and experimental research designs to understand behavior . In:  Introduction to Psychology . Minneapolis, MN: University of Minnesota Libraries Publishing; 2010.

Caruana EJ, Roman M, Herandez-Sanchez J, Solli P. Longitudinal studies . Journal of Thoracic Disease. 2015;7(11):E537-E540. doi:10.3978/j.issn.2072-1439.2015.10.63

University of Berkeley. Science at multiple levels . Understanding Science 101 . Published 2012.

By Kendra Cherry, MSEd Kendra Cherry, MS, is a psychosocial rehabilitation specialist, psychology educator, and author of the "Everything Psychology Book."

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

Chapter 3: Developing a Research Question

3.2 Exploration, Description, Explanation

As you can see, there is much to think about and many decisions to be made as you begin to define your research question and your research project. Something else you will need to consider in the early stages is whether your research will be exploratory, descriptive, or explanatory. Each of these types of research has a different aim or purpose, consequently, how you design your research project will be determined in part by this decision. In the following paragraphs we will look at these three types of research.

Exploratory research

Researchers conducting exploratory research are typically at the early stages of examining their topics. These sorts of projects are usually conducted when a researcher wants to test the feasibility of conducting a more extensive study; he or she wants to figure out the lay of the land with respect to the particular topic. Perhaps very little prior research has been conducted on this subject. If this is the case, a researcher may wish to do some exploratory work to learn what method to use in collecting data, how best to approach research participants, or even what sorts of questions are reasonable to ask. A researcher wanting to simply satisfy his or her own curiosity about a topic could also conduct exploratory research. Conducting exploratory research on a topic is often a necessary first step, both to satisfy researcher curiosity about the subject and to better understand the phenomenon and the research participants in order to design a larger, subsequent study. See Table 2.1 for examples.

Descriptive research

Sometimes the goal of research is to describe or define a particular phenomenon. In this case, descriptive research would be an appropriate strategy. A descriptive may, for example, aim to describe a pattern. For example, researchers often collect information to describe something for the benefit of the general public. Market researchers rely on descriptive research to tell them what consumers think of their products. In fact, descriptive research has many useful applications, and you probably rely on findings from descriptive research without even being aware that that is what you are doing. See Table 3.1 for examples.

Explanatory research

The third type of research, explanatory research, seeks to answer “why” questions. In this case, the researcher is trying to identify the causes and effects of whatever phenomenon is being studied. An explanatory study of college students’ addictions to their electronic gadgets, for example, might aim to understand why students become addicted. Does it have anything to do with their family histories? Does it have anything to do with their other extracurricular hobbies and activities? Does it have anything to do with the people with whom they spend their time? An explanatory study could answer these kinds of questions. See Table 3.1 for examples.

Table 3.1 Exploratory, descriptive and explanatory research differences (Adapted from Adjei, n.d.).

Research Methods for the Social Sciences: An Introduction Copyright © 2020 by Valerie Sheppard is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

• Survey Software The world’s leading omnichannel survey software
• Online Survey Tools Create sophisticated surveys with ease.
• Mobile Offline Conduct efficient field surveys.
• Text Analysis
• Close The Loop
• Automated Translations
• NPS Dashboard
• CATI Manage high volume phone surveys efficiently
• Cloud/On-premise Dialer TCPA compliant Cloud on-premise dialer
• IVR Survey Software Boost productivity with automated call workflows.
• Analytics Analyze survey data with visual dashboards
• Panel Manager Nurture a loyal community of respondents.
• Survey Portal Best-in-class user friendly survey portal.
• Voxco Audience Conduct targeted sample research in hours.
• Predictive Analytics
• Customer 360
• Customer Loyalty
• Fraud & Risk Management
• AI/ML Enablement Services
• Credit Underwriting

Find the best survey software for you! (Along with a checklist to compare platforms)

Get Buyer’s Guide

• 100+ question types
• Drag-and-drop interface
• Skip logic and branching
• Multi-lingual survey
• Text piping
• Question library
• CSS customization
• White-label surveys
• Customizable ‘Thank You’ page
• Customizable survey theme
• Reminder send-outs
• Survey rewards
• Social media
• SMS surveys
• Website surveys
• Correlation analysis
• Cross-tabulation analysis
• Trend analysis
• Real-time dashboard
• Customizable report
• Email address validation
• Recaptcha validation
• SSL security

Take a peek at our powerful survey features to design surveys that scale discoveries.

Download feature sheet.

• Hospitality
• Financial Services
• Academic Research
• Customer Experience
• Employee Experience
• Product Experience
• Market Research
• Social Research
• Data Analysis
• Banking & Financial Services
• Retail Solution
• Risk Management
• Customer Lifecycle Solutions
• Net Promoter Score
• Customer Behaviour Analytics
• Customer Segmentation
• Data Unification

Explore Voxco 

Need to map Voxco’s features & offerings? We can help!

Watch a Demo 

Download Brochures 

Get a Quote

• NPS Calculator
• CES Calculator
• A/B Testing Calculator
• Margin of Error Calculator
• Sample Size Calculator
• CX Strategy & Management Hub
• Market Research Hub
• Patient Experience Hub
• Employee Experience Hub
• Market Research Guide
• Customer Experience Guide
• The Voxco Guide to Customer Experience
• NPS Knowledge Hub
• Survey Research Guides
• Survey Template Library
• Webinars and Events
• Feature Sheets
• Try a sample survey
• Professional services
• Blogs & White papers
• Case Studies

Find the best customer experience platform

Uncover customer pain points, analyze feedback and run successful CX programs with the best CX platform for your team.

Get the Guide Now

We’ve been avid users of the Voxco platform now for over 20 years. It gives us the flexibility to routinely enhance our survey toolkit and provides our clients with a more robust dataset and story to tell their clients.

VP Innovation & Strategic Partnerships, The Logit Group

• Client Stories
• Voxco Reviews
• Why Voxco Research?
• Why Voxco Intelligence?
• Careers at Voxco
• Vulnerabilities and Ethical Hacking

Explore Regional Offices

• Cloud/On-premise Dialer TCPA compliant Cloud & on-premise dialer
• Fraud & Risk Management

Get Buyer’s Guide

• Banking & Financial Services

Explore Voxco 

Watch a Demo 

Download Brochures 

• CX Strategy & Management Hub
• Blogs & White papers

VP Innovation & Strategic Partnerships, The Logit Group

• Our clients
• Client stories
• Featuresheets

Descriptive Research: Definition, Methods & Examples

• August 19, 2021

Voxco’s Descriptive Research guide helps uncover the how, when, what, and where questions in a research problem

SHARE THE ARTICLE ON

When you are a store manager in a convenience store, and you have to make a report. Any finding such as which product is selling most, what time of the day you have the most crowd, or which product customers are demanding most, all these observations and reporting is descriptive research. 

It is often the first step of any research since the data you gather sets the stage for the research question. It is used to determine the problem you want to explore before fully realizing it. The information helps you identify the problem. 

In this blog, we’ll discuss the characteristics, types, pros & cons, and three ways to conduct this research type to help you in your next market research.

What is descriptive research?

Descriptive research refers to the research method that describes the characteristics of the variables you are studying. This methodology focuses on answering questions to the “WHAT” than the “WHY” of the research question. The primary focus of this research method is to describe the nature of the demographics understudy instead of focusing on the “why”.

It is called an observational research method as none of the variables in the study are influenced during the research process.

For example, let’s assume that a UK-based brand is trying to establish itself in New York and wants to understand the demographics of the buyers who generally purchase from brands similar to it. 

In descriptive research, the information gathered from the survey will only focus on the population’s demographics. It will uncover details on the buying patterns of different age cohorts in New York. It will not study why such patterns exist because the brand is trying to establish itself in New York. 

They want to understand the buying behavior of the population, not why such associations exist. It is a part of quantitative market research or social research study, which involves conducting survey research using quantitative variables on a market research software or social research software .

Voxco’s omnichannel survey software helps you collect insights from multiple channels using a single platform.

See the true power of using an integrated survey platform to conduct online, offline, and phone surveys along with a built-in analytical suite.

What are the characteristics of descriptive research?

Among the many, the following are the main characteristics of this research type:

• Quantitative research
• Nature of variables
• Cross-sectional studies
• Directs future research

Let’s discuss these four characteristics in detail. 

1. Quantitative research:

It is quantitative as it attempts to collect and statistically analyze information. This research type is a powerful research tool that permits a researcher to collect data and describe the demographics of the same with the help of statistical analysis. Thus, it is a quantitative research method .

2. Nature of variables:

The variables included in this research are uncontrolled. They are not manipulated in any way. Descriptive research mostly uses observational methods; thus, the researcher cannot control the nature and behavior of the variables under study.

3. Cross-sectional studies:

In this research type, different sections of the same group are studied. For instance, in order to study the fashion preferences of New York, the researcher can study Gen Z as well as Millennials from the same population in New York.

4. Directs future research:

Since this research identifies the patterns between variables and describes them, researchers can further study the data collected here. It guides researchers to discover further why such patterns have been found and their association. Hence, it gives researchers a direction toward insightful market research.

What are the methods of conducting descriptive research?

Primarily, there are three descriptive research methods: 

• Observation,
• Survey, & 

We have explained how you can conduct this research type in three different ways. Each method helps gather descriptive data and sets the scene for thorough research.

1. Observational method

All research has some component of observation, this observation can be quantitative or qualitative. A quantitative observation includes objectively collecting data that is primarily in numerical form. 

The data collected should be related to or understood in terms of quantity.

Quantitative observations are analyzed with the help of survey analytics software . 

Examples of quantitative observations include observation of any variable related to a numerical value such as age, shape, weight, height, scale, etc.

For example, a researcher can understand a customer’s satisfaction with their recent purchases by asking them to rate their satisfaction on a Likert scale ranging from 1 (extremely unsatisfied) to 7 (extremely satisfied).

Qualitative observations monitor the characteristics of a phenomenon and do not involve numerical measurements.

Using this type of descriptive research, you can observe respondents in a naturalistic environment from a distance. Since the respondents are in a natural environment, the observed characteristics enrich and offer more insights. 

For instance, you can monitor and note down the observations of customers in a supermarket by observing their selection and purchasing patterns. This offers a detailed cognizance of the customer.

In any kind of research, you should ensure high survey response rates for improved quality of insights.  

2. Survey method

The survey method includes recording the answers of respondents through surveys or questionnaires. Surveys can include polls as well. They are the most common tool for collecting market research data. 

Surveys are generally used to collect feedback from the respondents. It should have a survey that taps into both open-ended and closed-ended questions .

The biggest advantage of the survey method is that it can be conducted using online or offline survey tools . One of the reasons why the survey method is the go-to option for descriptive research is that it entails the collection of large amounts of data in a limited span of time.

3. Case study method

The in-depth study of an individual or a group is known as a case study. Case studies usually lead to developing a hypothesis to explore a phenomenon further. Case studies are limited in their scope in that they don’t allow the researcher to make cause-effect conclusions or accurate predictions. 

This is because these associations could reflect the bias on the researchers’ part instead of a naturally occurring phenomenon. Another reason why case studies are limited in scope is that they could just be reflecting an atypical respondent in the survey. 

An atypical respondent refers to someone who is different from the average consumer, and if researchers make judgments about the entire target population based on this consumer, it can affect the external validity of the study.

[ Related read: Descriptive vs experimental research ]

Read how Voxco helped Brain Research improve research productivity by 60%.

“The platform extends our ability to productively manage our busy intercept survey projects, and the confidence to support major new clients.”

Laura Ruvalcaba, President & CEO, Brain Research

What are the types of descriptive research?

There are seven types of descriptive research based on when you conduct them and what type of data research you conduct. We have explained these seven types in brief with examples to help you better understand them.

1. Cross-sectional: 

A descriptive method of studying a particular section of the target population at a specific point in time. 

Example : Tracking the use of social media by Gen Z in the Netherlands. 

2. Longitudinal: 

This type of descriptive study is conducted for an extended period on a group of people. 

Example : Monitoring changes in the volume of cyber-bullying among Millenials from 2022 to 2024. 

3. Normative: 

In this descriptive method, we compare the result of a study with an existing norm. 

Example : Comparing legal verdicts in similar types of cases. 

4. Relational/Correlational:

We investigate the type of relationships (correlation) between two variables in this type of descriptive research. 

Example : Investigating the relationship between video games and mental health. 

5. Comparative: 

A descriptive study that compares two or more people, groups, or conditions based on a specific aspect. 

Example : Comparing the salary of two employees in similar job roles from two companies. 

6. Classification: 

This type of research arranges collected data into classes based on specific criteria to analyze them. 

Example : Classification of customers based on their buying behavior. 

7. Archival: 

A descriptive study where you search for past records and extract information.

Example : Tracking company’s sales data over the decade. 

We have been discussing the descriptive method with examples. So now let’s see how you can use this research type in a real-world application.

Guide to Descriptive Research

Learn the key steps of conducting descriptive research to uncover breakthrough insights into your target market.

Examples of Descriptive Research Under Market Research

This research type helps you gather the necessary information you need to understand the problem. It sets the scene to conduct further research. But how can you use this research method in the real world? 

We have explained its real-world application in three scenarios to help you determine where and where you want to use this research type. 

1. Sales Studies

You can use this research type to analyze the potential of the market, what is currently trending in the market, and which products may perform well in terms of sales. You can also study what circumstances influence the market shares and when they are likely to increase or decrease. 

This research type can help you gather the demographic data of the consumers.

2. Consumer Perception and Behavior Studies

You can use this research method to analyze what consumers think about the brand. You can evaluate their perceptions about the products sold by a particular brand and the uses of other competitive products. 

Using descriptive research, you can also analyze what advertising strategies have worked to increase the positive perceptions of the brand. You can assess consumers’ consumption behavior and how it is influenced by product pricing.

3. Market Characteristics Studies

Another way you can use this research method is by analyzing the distribution of the products in the market. You can gather contextual data on questions such as “which countries have more sales”, “which countries have fewer products but the product is sold out quickly” , etc. 

You can also analyze the brand management of competitors ; what strategy is working for them and what is not.

What are the applications of descriptive research?

This research method is used for a variety of reasons. Even after outlining survey goals, and survey designs as well as collecting information through surveys, there is no way of knowing whether or not the research you are conducting will meet the predictions that you have made. 

Here are some popular ways in which organizations use this research type:

1. Defining the characteristics of respondents

Since most descriptive research methods use close-ended questions for the collection of data, it helps in drawing objective conclusions about the respondents.

It helps in deriving patterns, traits, and behaviors of respondents. It also aims to understand respondents’ attitudes and opinions about certain phenomena.

For instance , researchers can understand how many hours young adults spend on the internet, their opinions about social media platforms, and how important they consider these platforms to be. This information will help the company make informed decisions regarding its products and brands. 

One-stop-shop to gather, measure, uncover, and act on insightful data.

Curious about the price? Click below to get a personalized quote.

2. Analyzing trends in data

You can use statistical data analysis to understand the trends in data over time. 

For instance, consider an apparel company that drops a new line of clothing; they may research how Gen Z and Millennials react to the new launch. If they discover that the new range of clothes has worked effectively for one group (Gen Z) but not the other, the company may stop producing clothes for the other group.

Leverage a data analysis platform that allows you to conduct advanced statistical analysis and offers a data analytics dashboard to track real-time data.

3. Comparing different groups

Something closely knit to the previous point is also comparing different groups of customers based on their demographics. With descriptive research, you can study how different groups of people respond to specific services offered by a company. 

For instance , what is the influence of income, age, gender, income, etc. influence the spending behaviors of consumers?

This research method helps companies understand what they should do to increase their brand appeal in different groups of the population. 

4. Validating existing patterns of respondents

Since it is non-invasive and makes use of quantitative data (mostly), you can make observations about why the current patterns of purchasing exist in customers. 

You can also use the findings as the basis of a more in-depth study in the future. 

5. Conducting research at different times

Descriptive research can be conducted at different periods of time in order to see whether the patterns are similar or dissimilar at different points in time. You can also replicate the studies to verify the findings of the original study to draw accurate conclusions.

6. Finding correlations among variables

This method is also used to draw correlations between variables and the degree of association between the variables. 

For instance, if the focus is on men’s age and expenditure. 

There is a possibility of finding a negative correlation between the two variables, indicating that as the age of men increases, the less they spend on sports products.

Download Market Research Tool kit

5 MR templates + MR trends guide + Online survey guide + Agile MR guide

Descriptive research Examples

A descriptive method of research aims to gather answers for how, what, when, and where. 

Let’s use some examples to understand how a descriptive method of research is used. 

Before investing in housing at any location, you would want to conduct your own research to understand 

• How is the market changing?
• When or at what time of year is it changing?
• Where would you make more profit?

This type of research is an example of a descriptive study. 

A company studies the behavior of its customers to identify its target market before it launches a new product. This is another use case of how brands use descriptive research. 

The company may conduct this research by observing the customer’s reaction and behavior toward a competitor’s product. 

Or, they can also conduct surveys to ask customer opinions on the new product by the company before its launch. 

A restaurant planning to open a branch in a new locality will research to understand the behavior of the people living there. They will survey the people to know their choice of flavor, taste, foods, drinks, and more. 

Now that we’ve seen how you can use this research method for your research purpose, let’s also see the advantages & disadvantages of the research.

What Are the Advantages of Descriptive Research?

It is the preliminary research method. Most researchers use this method to discover the problem they should prioritize. Before diving into the experiments, let’s see some of the reasons why you should be conducting this research. 

1. Primary data collection

In this type of descriptive research, the data is collected through primary data collection methods such as case studies, observational methods, and surveys. This kind of data collection provides us with rich information and can be used for future research as well. It can also be used for developing hypotheses or your research objective.

2. Multiple data collection

Descriptive research can also be conducted by collecting qualitative or quantitative data . Hence, it is more varied, flexible, and diverse and tends to be thorough and elaborate.

[ Related read: Data Collection: All you need to know! ]

3. Observational behavior 

The observational method of this research allows researchers to observe the respondent’s behavior in natural settings. This also ensures that the data collected is high in quality and honest.

4. Cost-effective

It is cost-effective and the data collection of this research can be done quickly. You can conduct descriptive research using an all-in-one solution such as Voxco. Leverage a platform that gives you the capability of the best market research software to conduct customer, product, and brand research.

What Are the Disadvantages of Descriptive Research?

Descriptive research also has some disadvantages. Let’s learn about these cons so you can wisely decide when you should use this research to keep the disadvantages to a minimum. 

1. Misleading information

Respondents can give misleading or incorrect responses if they feel that the questions are assessing intimate matters. Respondents can also be affected by the observer’s presence and may engage in pretending. This is known as the observer effect.

2. Biases in studies

The researchers’ own opinions of biases may affect the results of the study. This is known as the experimenter effect.

3. Representative issue 

There is also the problem of data representativeness. It occurs when a case study or the data of a small sample does not adequately represent the whole population.

4. Limited scope

Descriptive research has limited scope, wherein it only analyzes the “what” of research, it does not evaluate the “why” or “how” questions of research.

Voxco is trusted by 500+ global brands and top 50 MR firms to gather insights and take actions.

See how Voxco can help enhance your research efficiency.

Wrapping up;

So that sums up our descriptive research guide. It is a wide concept that demands a conceptual framework for descriptive design and a thorough understanding of descriptive survey design . 

Naturally, it becomes essential that you adopt online survey tools that facilitates all of the above and provides ample room for insightful research.  

Voxco’s omnichannel survey software allows you to create interactive surveys, deploy them across multiple channels, and conduct data analysis in one platform.

This research method enables you to explain and describe the characteristics of a target population. The descriptive research method helps you uncover deeper insights into various aspects of the target population, such as who, what, when, where, and how. 

There are many data collection methods you can use to collect descriptive research data. For example, you can perform the research via surveys (online, phone, or offline), case studies, observations, and archival research.

Here are some key characteristics of this research methodology: 

This research type helps you describe the characteristics, behavior, opinions, and perspectives of the population or research subject. 

The data gathered from descriptive research is a reliable and comprehensive source of explanation of the research subject. 

In this methodology, the researcher focuses on observing and reporting on the natural relationship between the variables. There is no manipulation of variables or establishing a cause-and-effect relationship.

Descriptive research offers many advantages. 

Descriptive research methods are simple and easy to design and conduct. You don’t need research expertise for this research design in comparison to conducting more complex research. 

This research method is more cost-effective than other research methodologies, particularly experimental research designs. 

The descriptive research method enables you to collect qualitative and quantitative data. The research data helps extract valuable insights and supports further root-cause analysis.

Descriptive research methodology also has some limitations, here are some of those: 

Descriptive research data may generate insights specific to a population under study. This limits your ability to generalize the results to a wider population, which makes the data less representative. 

The data collection approaches and observation biases can lead to bias in the research method, which can negatively impact the accuracy and reliability of the research findings.

Join the network of 500+ happy survey creators.

Explore all the survey question types possible on Voxco

Explore Voxco Survey Software

+ Omnichannel Survey Software 

+ Online Survey Software 

+ CATI Survey Software 

+ IVR Survey Software 

+ Market Research Tool

+ Customer Experience Tool 

+ Product Experience Software 

+ Enterprise Survey Software 

21 Market Research Tools you should be looking at in 2021

21 Market Research Tools you should be looking at in 2021 The Ultimate Guide to Cluster Sampling Get a step-by-step guide for choosing the correct

Regression Testing

Regression Testing SHARE THE ARTICLE ON Share on facebook Share on twitter Share on linkedin Table of Contents What is Regression Testing? When software developers

Double-Blind Study

Double-Blind Study 101: Unbiased Research Excellence SHARE THE ARTICLE ON See what question types are possible with a sample survey! Try a Sample Survey Table

Survey Panel Management

Survey Panel Management Transform your insight generation process Use our in-depth online survey guide to create an actionable feedback collection survey process. Download Now SHARE

Retail banking customer experience

Retail banking customer experience SHARE THE ARTICLE ON Table of Contents What is customer experience in banking? As the name suggests, customer experience in banking

Concept Testing Definition, Examples & Tips

Concept Testing Definition, Examples & Tips SHARE THE ARTICLE ON Share on facebook Share on twitter Share on linkedin Table of Contents Introduction to Concept

We use cookies in our website to give you the best browsing experience and to tailor advertising. By continuing to use our website, you give us consent to the use of cookies. Read More

Looking for the best research tools?

Voxco offers the best online & offline survey research tools!

Research Methods In Psychology

Saul Mcleod, PhD

Editor-in-Chief for Simply Psychology

BSc (Hons) Psychology, MRes, PhD, University of Manchester

Saul Mcleod, PhD., is a qualified psychology teacher with over 18 years of experience in further and higher education. He has been published in peer-reviewed journals, including the Journal of Clinical Psychology.

Learn about our Editorial Process

Olivia Guy-Evans, MSc

Associate Editor for Simply Psychology

BSc (Hons) Psychology, MSc Psychology of Education

Olivia Guy-Evans is a writer and associate editor for Simply Psychology. She has previously worked in healthcare and educational sectors.

Research methods in psychology are systematic procedures used to observe, describe, predict, and explain behavior and mental processes. They include experiments, surveys, case studies, and naturalistic observations, ensuring data collection is objective and reliable to understand and explain psychological phenomena.

Hypotheses are statements about the prediction of the results, that can be verified or disproved by some investigation.

There are four types of hypotheses :

• Null Hypotheses (H0 ) – these predict that no difference will be found in the results between the conditions. Typically these are written ‘There will be no difference…’
• Alternative Hypotheses (Ha or H1) – these predict that there will be a significant difference in the results between the two conditions. This is also known as the experimental hypothesis.
• One-tailed (directional) hypotheses – these state the specific direction the researcher expects the results to move in, e.g. higher, lower, more, less. In a correlation study, the predicted direction of the correlation can be either positive or negative.
• Two-tailed (non-directional) hypotheses – these state that a difference will be found between the conditions of the independent variable but does not state the direction of a difference or relationship. Typically these are always written ‘There will be a difference ….’

All research has an alternative hypothesis (either a one-tailed or two-tailed) and a corresponding null hypothesis.

Once the research is conducted and results are found, psychologists must accept one hypothesis and reject the other. 

So, if a difference is found, the Psychologist would accept the alternative hypothesis and reject the null.  The opposite applies if no difference is found.

Sampling techniques

Sampling is the process of selecting a representative group from the population under study.

A sample is the participants you select from a target population (the group you are interested in) to make generalizations about.

Representative means the extent to which a sample mirrors a researcher’s target population and reflects its characteristics.

Generalisability means the extent to which their findings can be applied to the larger population of which their sample was a part.

• Volunteer sample : where participants pick themselves through newspaper adverts, noticeboards or online.
• Opportunity sampling : also known as convenience sampling , uses people who are available at the time the study is carried out and willing to take part. It is based on convenience.
• Random sampling : when every person in the target population has an equal chance of being selected. An example of random sampling would be picking names out of a hat.
• Systematic sampling : when a system is used to select participants. Picking every Nth person from all possible participants. N = the number of people in the research population / the number of people needed for the sample.
• Stratified sampling : when you identify the subgroups and select participants in proportion to their occurrences.
• Snowball sampling : when researchers find a few participants, and then ask them to find participants themselves and so on.
• Quota sampling : when researchers will be told to ensure the sample fits certain quotas, for example they might be told to find 90 participants, with 30 of them being unemployed.

Experiments always have an independent and dependent variable .

• The independent variable is the one the experimenter manipulates (the thing that changes between the conditions the participants are placed into). It is assumed to have a direct effect on the dependent variable.
• The dependent variable is the thing being measured, or the results of the experiment.

Operationalization of variables means making them measurable/quantifiable. We must use operationalization to ensure that variables are in a form that can be easily tested.

For instance, we can’t really measure ‘happiness’, but we can measure how many times a person smiles within a two-hour period. 

By operationalizing variables, we make it easy for someone else to replicate our research. Remember, this is important because we can check if our findings are reliable.

Extraneous variables are all variables which are not independent variable but could affect the results of the experiment.

It can be a natural characteristic of the participant, such as intelligence levels, gender, or age for example, or it could be a situational feature of the environment such as lighting or noise.

Demand characteristics are a type of extraneous variable that occurs if the participants work out the aims of the research study, they may begin to behave in a certain way.

For example, in Milgram’s research , critics argued that participants worked out that the shocks were not real and they administered them as they thought this was what was required of them. 

Extraneous variables must be controlled so that they do not affect (confound) the results.

Randomly allocating participants to their conditions or using a matched pairs experimental design can help to reduce participant variables. 

Situational variables are controlled by using standardized procedures, ensuring every participant in a given condition is treated in the same way

Experimental Design

Experimental design refers to how participants are allocated to each condition of the independent variable, such as a control or experimental group.

• Independent design ( between-groups design ): each participant is selected for only one group. With the independent design, the most common way of deciding which participants go into which group is by means of randomization. 
• Matched participants design : each participant is selected for only one group, but the participants in the two groups are matched for some relevant factor or factors (e.g. ability; sex; age).
• Repeated measures design ( within groups) : each participant appears in both groups, so that there are exactly the same participants in each group.
• The main problem with the repeated measures design is that there may well be order effects. Their experiences during the experiment may change the participants in various ways.
• They may perform better when they appear in the second group because they have gained useful information about the experiment or about the task. On the other hand, they may perform less well on the second occasion because of tiredness or boredom.
• Counterbalancing is the best way of preventing order effects from disrupting the findings of an experiment, and involves ensuring that each condition is equally likely to be used first and second by the participants.

If we wish to compare two groups with respect to a given independent variable, it is essential to make sure that the two groups do not differ in any other important way. 

Experimental Methods

All experimental methods involve an iv (independent variable) and dv (dependent variable)..

• Field experiments are conducted in the everyday (natural) environment of the participants. The experimenter still manipulates the IV, but in a real-life setting. It may be possible to control extraneous variables, though such control is more difficult than in a lab experiment.
• Natural experiments are when a naturally occurring IV is investigated that isn’t deliberately manipulated, it exists anyway. Participants are not randomly allocated, and the natural event may only occur rarely.

Case studies are in-depth investigations of a person, group, event, or community. It uses information from a range of sources, such as from the person concerned and also from their family and friends.

Many techniques may be used such as interviews, psychological tests, observations and experiments. Case studies are generally longitudinal: in other words, they follow the individual or group over an extended period of time. 

Case studies are widely used in psychology and among the best-known ones carried out were by Sigmund Freud . He conducted very detailed investigations into the private lives of his patients in an attempt to both understand and help them overcome their illnesses.

Case studies provide rich qualitative data and have high levels of ecological validity. However, it is difficult to generalize from individual cases as each one has unique characteristics.

Correlational Studies

Correlation means association; it is a measure of the extent to which two variables are related. One of the variables can be regarded as the predictor variable with the other one as the outcome variable.

Correlational studies typically involve obtaining two different measures from a group of participants, and then assessing the degree of association between the measures. 

The predictor variable can be seen as occurring before the outcome variable in some sense. It is called the predictor variable, because it forms the basis for predicting the value of the outcome variable.

Relationships between variables can be displayed on a graph or as a numerical score called a correlation coefficient.

• If an increase in one variable tends to be associated with an increase in the other, then this is known as a positive correlation .
• If an increase in one variable tends to be associated with a decrease in the other, then this is known as a negative correlation .
• A zero correlation occurs when there is no relationship between variables.

After looking at the scattergraph, if we want to be sure that a significant relationship does exist between the two variables, a statistical test of correlation can be conducted, such as Spearman’s rho.

The test will give us a score, called a correlation coefficient . This is a value between 0 and 1, and the closer to 1 the score is, the stronger the relationship between the variables. This value can be both positive e.g. 0.63, or negative -0.63.

A correlation between variables, however, does not automatically mean that the change in one variable is the cause of the change in the values of the other variable. A correlation only shows if there is a relationship between variables.

Correlation does not always prove causation, as a third variable may be involved. 

Interview Methods

Interviews are commonly divided into two types: structured and unstructured.

A fixed, predetermined set of questions is put to every participant in the same order and in the same way. 

Responses are recorded on a questionnaire, and the researcher presets the order and wording of questions, and sometimes the range of alternative answers.

The interviewer stays within their role and maintains social distance from the interviewee.

There are no set questions, and the participant can raise whatever topics he/she feels are relevant and ask them in their own way. Questions are posed about participants’ answers to the subject

Unstructured interviews are most useful in qualitative research to analyze attitudes and values.

Though they rarely provide a valid basis for generalization, their main advantage is that they enable the researcher to probe social actors’ subjective point of view. 

Questionnaire Method

Questionnaires can be thought of as a kind of written interview. They can be carried out face to face, by telephone, or post.

The choice of questions is important because of the need to avoid bias or ambiguity in the questions, ‘leading’ the respondent or causing offense.

• Open questions are designed to encourage a full, meaningful answer using the subject’s own knowledge and feelings. They provide insights into feelings, opinions, and understanding. Example: “How do you feel about that situation?”
• Closed questions can be answered with a simple “yes” or “no” or specific information, limiting the depth of response. They are useful for gathering specific facts or confirming details. Example: “Do you feel anxious in crowds?”

Its other practical advantages are that it is cheaper than face-to-face interviews and can be used to contact many respondents scattered over a wide area relatively quickly.

Observations

There are different types of observation methods :

• Covert observation is where the researcher doesn’t tell the participants they are being observed until after the study is complete. There could be ethical problems or deception and consent with this particular observation method.
• Overt observation is where a researcher tells the participants they are being observed and what they are being observed for.
• Controlled : behavior is observed under controlled laboratory conditions (e.g., Bandura’s Bobo doll study).
• Natural : Here, spontaneous behavior is recorded in a natural setting.
• Participant : Here, the observer has direct contact with the group of people they are observing. The researcher becomes a member of the group they are researching.  
• Non-participant (aka “fly on the wall): The researcher does not have direct contact with the people being observed. The observation of participants’ behavior is from a distance

Pilot Study

A pilot  study is a small scale preliminary study conducted in order to evaluate the feasibility of the key s teps in a future, full-scale project.

A pilot study is an initial run-through of the procedures to be used in an investigation; it involves selecting a few people and trying out the study on them. It is possible to save time, and in some cases, money, by identifying any flaws in the procedures designed by the researcher.

A pilot study can help the researcher spot any ambiguities (i.e. unusual things) or confusion in the information given to participants or problems with the task devised.

Sometimes the task is too hard, and the researcher may get a floor effect, because none of the participants can score at all or can complete the task – all performances are low.

The opposite effect is a ceiling effect, when the task is so easy that all achieve virtually full marks or top performances and are “hitting the ceiling”.

Research Design

In cross-sectional research , a researcher compares multiple segments of the population at the same time

Sometimes, we want to see how people change over time, as in studies of human development and lifespan. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time.

In cohort studies , the participants must share a common factor or characteristic such as age, demographic, or occupation. A cohort study is a type of longitudinal study in which researchers monitor and observe a chosen population over an extended period.

Triangulation means using more than one research method to improve the study’s validity.

Reliability

Reliability is a measure of consistency, if a particular measurement is repeated and the same result is obtained then it is described as being reliable.

• Test-retest reliability :  assessing the same person on two different occasions which shows the extent to which the test produces the same answers.
• Inter-observer reliability : the extent to which there is an agreement between two or more observers.

Meta-Analysis

A meta-analysis is a systematic review that involves identifying an aim and then searching for research studies that have addressed similar aims/hypotheses.

This is done by looking through various databases, and then decisions are made about what studies are to be included/excluded.

Strengths: Increases the conclusions’ validity as they’re based on a wider range.

Weaknesses: Research designs in studies can vary, so they are not truly comparable.

Peer Review

A researcher submits an article to a journal. The choice of the journal may be determined by the journal’s audience or prestige.

The journal selects two or more appropriate experts (psychologists working in a similar field) to peer review the article without payment. The peer reviewers assess: the methods and designs used, originality of the findings, the validity of the original research findings and its content, structure and language.

Feedback from the reviewer determines whether the article is accepted. The article may be: Accepted as it is, accepted with revisions, sent back to the author to revise and re-submit or rejected without the possibility of submission.

The editor makes the final decision whether to accept or reject the research report based on the reviewers comments/ recommendations.

Peer review is important because it prevent faulty data from entering the public domain, it provides a way of checking the validity of findings and the quality of the methodology and is used to assess the research rating of university departments.

Peer reviews may be an ideal, whereas in practice there are lots of problems. For example, it slows publication down and may prevent unusual, new work being published. Some reviewers might use it as an opportunity to prevent competing researchers from publishing work.

Some people doubt whether peer review can really prevent the publication of fraudulent research.

The advent of the internet means that a lot of research and academic comment is being published without official peer reviews than before, though systems are evolving on the internet where everyone really has a chance to offer their opinions and police the quality of research.

Types of Data

• Quantitative data is numerical data e.g. reaction time or number of mistakes. It represents how much or how long, how many there are of something. A tally of behavioral categories and closed questions in a questionnaire collect quantitative data.
• Qualitative data is virtually any type of information that can be observed and recorded that is not numerical in nature and can be in the form of written or verbal communication. Open questions in questionnaires and accounts from observational studies collect qualitative data.
• Primary data is first-hand data collected for the purpose of the investigation.
• Secondary data is information that has been collected by someone other than the person who is conducting the research e.g. taken from journals, books or articles.

Validity means how well a piece of research actually measures what it sets out to, or how well it reflects the reality it claims to represent.

Validity is whether the observed effect is genuine and represents what is actually out there in the world.

• Concurrent validity is the extent to which a psychological measure relates to an existing similar measure and obtains close results. For example, a new intelligence test compared to an established test.
• Face validity : does the test measure what it’s supposed to measure ‘on the face of it’. This is done by ‘eyeballing’ the measuring or by passing it to an expert to check.
• Ecological validit y is the extent to which findings from a research study can be generalized to other settings / real life.
• Temporal validity is the extent to which findings from a research study can be generalized to other historical times.

Features of Science

• Paradigm – A set of shared assumptions and agreed methods within a scientific discipline.
• Paradigm shift – The result of the scientific revolution: a significant change in the dominant unifying theory within a scientific discipline.
• Objectivity – When all sources of personal bias are minimised so not to distort or influence the research process.
• Empirical method – Scientific approaches that are based on the gathering of evidence through direct observation and experience.
• Replicability – The extent to which scientific procedures and findings can be repeated by other researchers.
• Falsifiability – The principle that a theory cannot be considered scientific unless it admits the possibility of being proved untrue.

Statistical Testing

A significant result is one where there is a low probability that chance factors were responsible for any observed difference, correlation, or association in the variables tested.

If our test is significant, we can reject our null hypothesis and accept our alternative hypothesis.

If our test is not significant, we can accept our null hypothesis and reject our alternative hypothesis. A null hypothesis is a statement of no effect.

In Psychology, we use p < 0.05 (as it strikes a balance between making a type I and II error) but p < 0.01 is used in tests that could cause harm like introducing a new drug.

A type I error is when the null hypothesis is rejected when it should have been accepted (happens when a lenient significance level is used, an error of optimism).

A type II error is when the null hypothesis is accepted when it should have been rejected (happens when a stringent significance level is used, an error of pessimism).

Ethical Issues

• Informed consent is when participants are able to make an informed judgment about whether to take part. It causes them to guess the aims of the study and change their behavior.
• To deal with it, we can gain presumptive consent or ask them to formally indicate their agreement to participate but it may invalidate the purpose of the study and it is not guaranteed that the participants would understand.
• Deception should only be used when it is approved by an ethics committee, as it involves deliberately misleading or withholding information. Participants should be fully debriefed after the study but debriefing can’t turn the clock back.
• All participants should be informed at the beginning that they have the right to withdraw if they ever feel distressed or uncomfortable.
• It causes bias as the ones that stayed are obedient and some may not withdraw as they may have been given incentives or feel like they’re spoiling the study. Researchers can offer the right to withdraw data after participation.
• Participants should all have protection from harm . The researcher should avoid risks greater than those experienced in everyday life and they should stop the study if any harm is suspected. However, the harm may not be apparent at the time of the study.
• Confidentiality concerns the communication of personal information. The researchers should not record any names but use numbers or false names though it may not be possible as it is sometimes possible to work out who the researchers were.

Psychological Research

Descriptive research, learning objectives.

• Differentiate between descriptive, experimental, and correlational research
• Explain the strengths and weaknesses of case studies, naturalistic observation, and surveys

There are many research methods available to psychologists in their efforts to understand, describe, and explain behavior and the cognitive and biological processes that underlie it. Some methods rely on observational techniques. Other approaches involve interactions between the researcher and the individuals who are being studied—ranging from a series of simple questions to extensive, in-depth interviews—to well-controlled experiments.

The three main categories of psychological research are descriptive, correlational, and experimental research. Research studies that do not test specific relationships between variables are called descriptive studies . These studies are used to describe general or specific behaviors and attributes that are observed and measured. In the early stages of research, it might be difficult to form a hypothesis, especially when there is not any existing literature in the area. In these situations designing an experiment would be premature, as the question of interest is not yet clearly defined as a hypothesis. Often a researcher will begin with a non-experimental approach, such as a descriptive study, to gather more information about the topic before designing an experiment or correlational study to address a specific hypothesis. Descriptive research is distinct from correlational research , in which psychologists formally test whether a relationship exists between two or more variables. Experimental research goes a step further beyond descriptive and correlational research and randomly assigns people to different conditions, using hypothesis testing to make inferences about how these conditions affect behavior. It aims to determine if one variable directly impacts and causes another. Correlational and experimental research both typically use hypothesis testing, whereas descriptive research does not. Table 1 displays a quick overview of the characteristics of each research design.

Table 1. Characteristics of Descriptive, Experimental, and Correlational Research

Each of these research methods has unique strengths and weaknesses, and each method may only be appropriate for certain types of research questions. For example, studies that rely primarily on observation produce incredible amounts of information, but the ability to apply this information to the larger population is somewhat limited because of small sample sizes. Survey research, on the other hand, allows researchers to easily collect data from relatively large samples. While this allows for results to be generalized to the larger population more easily, the information that can be collected on any given survey is somewhat limited and subject to problems associated with any type of self-reported data. Some researchers conduct archival research by using existing records. While this can be a fairly inexpensive way to collect data that can provide insight into a number of research questions, researchers using this approach have no control on how or what kind of data was collected.

Correlational research can find a relationship between two variables, but the only way a researcher can claim that the relationship between the variables is cause and effect is to perform an experiment. In experimental research, which will be discussed later in the text, there is a tremendous amount of control over variables of interest. While this is a powerful approach, experiments are often conducted in very artificial settings. This calls into question the validity of experimental findings with regard to how they would apply in real-world settings. In addition, many of the questions that psychologists would like to answer cannot be pursued through experimental research because of ethical concerns.

The three main types of descriptive studies are case studies, naturalistic observation, and surveys.

Case Studies

In 2011, the New York Times published a feature story on Krista and Tatiana Hogan, Canadian twin girls. These particular twins are unique because Krista and Tatiana are conjoined twins, connected at the head. There is evidence that the two girls are connected in a part of the brain called the thalamus, which is a major sensory relay center. Most incoming sensory information is sent through the thalamus before reaching higher regions of the cerebral cortex for processing.

Link to Learning

To learn more about Krista and Tatiana, watch this video about their lives as conjoined twins.

The implications of this potential connection mean that it might be possible for one twin to experience the sensations of the other twin. For instance, if Krista is watching a particularly funny television program, Tatiana might smile or laugh even if she is not watching the program. This particular possibility has piqued the interest of many neuroscientists who seek to understand how the brain uses sensory information.

These twins represent an enormous resource in the study of the brain, and since their condition is very rare, it is likely that as long as their family agrees, scientists will follow these girls very closely throughout their lives to gain as much information as possible (Dominus, 2011).

In observational research, scientists are conducting a clinical or case study when they focus on one person or just a few individuals. Indeed, some scientists spend their entire careers studying just 10–20 individuals. Why would they do this? Obviously, when they focus their attention on a very small number of people, they can gain a tremendous amount of insight into those cases. The richness of information that is collected in clinical or case studies is unmatched by any other single research method. This allows the researcher to have a very deep understanding of the individuals and the particular phenomenon being studied.

If clinical or case studies provide so much information, why are they not more frequent among researchers? As it turns out, the major benefit of this particular approach is also a weakness. As mentioned earlier, this approach is often used when studying individuals who are interesting to researchers because they have a rare characteristic. Therefore, the individuals who serve as the focus of case studies are not like most other people. If scientists ultimately want to explain all behavior, focusing attention on such a special group of people can make it difficult to generalize any observations to the larger population as a whole. Generalizing refers to the ability to apply the findings of a particular research project to larger segments of society. Again, case studies provide enormous amounts of information, but since the cases are so specific, the potential to apply what’s learned to the average person may be very limited.

Naturalistic Observation

If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances are that almost everyone in the classroom will raise their hand, but do you think hand washing after every trip to the restroom is really that universal?

This is very similar to the phenomenon mentioned earlier in this module: many individuals do not feel comfortable answering a question honestly. But if we are committed to finding out the facts about hand washing, we have other options available to us.

Suppose we send a classmate into the restroom to actually watch whether everyone washes their hands after using the restroom. Will our observer blend into the restroom environment by wearing a white lab coat, sitting with a clipboard, and staring at the sinks? We want our researcher to be inconspicuous—perhaps standing at one of the sinks pretending to put in contact lenses while secretly recording the relevant information. This type of observational study is called naturalistic observation : observing behavior in its natural setting. To better understand peer exclusion, Suzanne Fanger collaborated with colleagues at the University of Texas to observe the behavior of preschool children on a playground. How did the observers remain inconspicuous over the duration of the study? They equipped a few of the children with wireless microphones (which the children quickly forgot about) and observed while taking notes from a distance. Also, the children in that particular preschool (a “laboratory preschool”) were accustomed to having observers on the playground (Fanger, Frankel, & Hazen, 2012).

Figure 1 . Seeing a police car behind you would probably affect your driving behavior. (credit: Michael Gil)

It is critical that the observer be as unobtrusive and as inconspicuous as possible: when people know they are being watched, they are less likely to behave naturally. If you have any doubt about this, ask yourself how your driving behavior might differ in two situations: In the first situation, you are driving down a deserted highway during the middle of the day; in the second situation, you are being followed by a police car down the same deserted highway (Figure 1).

It should be pointed out that naturalistic observation is not limited to research involving humans. Indeed, some of the best-known examples of naturalistic observation involve researchers going into the field to observe various kinds of animals in their own environments. As with human studies, the researchers maintain their distance and avoid interfering with the animal subjects so as not to influence their natural behaviors. Scientists have used this technique to study social hierarchies and interactions among animals ranging from ground squirrels to gorillas. The information provided by these studies is invaluable in understanding how those animals organize socially and communicate with one another. The anthropologist Jane Goodall, for example, spent nearly five decades observing the behavior of chimpanzees in Africa (Figure 2). As an illustration of the types of concerns that a researcher might encounter in naturalistic observation, some scientists criticized Goodall for giving the chimps names instead of referring to them by numbers—using names was thought to undermine the emotional detachment required for the objectivity of the study (McKie, 2010).

Figure 2 . (a) Jane Goodall made a career of conducting naturalistic observations of (b) chimpanzee behavior. (credit “Jane Goodall”: modification of work by Erik Hersman; “chimpanzee”: modification of work by “Afrika Force”/Flickr.com)

The greatest benefit of naturalistic observation is the validity, or accuracy, of information collected unobtrusively in a natural setting. Having individuals behave as they normally would in a given situation means that we have a higher degree of ecological validity, or realism, than we might achieve with other research approaches. Therefore, our ability to generalize the findings of the research to real-world situations is enhanced. If done correctly, we need not worry about people or animals modifying their behavior simply because they are being observed. Sometimes, people may assume that reality programs give us a glimpse into authentic human behavior. However, the principle of inconspicuous observation is violated as reality stars are followed by camera crews and are interviewed on camera for personal confessionals. Given that environment, we must doubt how natural and realistic their behaviors are.

The major downside of naturalistic observation is that they are often difficult to set up and control. In our restroom study, what if you stood in the restroom all day prepared to record people’s hand washing behavior and no one came in? Or, what if you have been closely observing a troop of gorillas for weeks only to find that they migrated to a new place while you were sleeping in your tent? The benefit of realistic data comes at a cost. As a researcher you have no control of when (or if) you have behavior to observe. In addition, this type of observational research often requires significant investments of time, money, and a good dose of luck.

Sometimes studies involve structured observation. In these cases, people are observed while engaging in set, specific tasks. An excellent example of structured observation comes from Strange Situation by Mary Ainsworth (you will read more about this in the module on lifespan development). The Strange Situation is a procedure used to evaluate attachment styles that exist between an infant and caregiver. In this scenario, caregivers bring their infants into a room filled with toys. The Strange Situation involves a number of phases, including a stranger coming into the room, the caregiver leaving the room, and the caregiver’s return to the room. The infant’s behavior is closely monitored at each phase, but it is the behavior of the infant upon being reunited with the caregiver that is most telling in terms of characterizing the infant’s attachment style with the caregiver.

Another potential problem in observational research is observer bias . Generally, people who act as observers are closely involved in the research project and may unconsciously skew their observations to fit their research goals or expectations. To protect against this type of bias, researchers should have clear criteria established for the types of behaviors recorded and how those behaviors should be classified. In addition, researchers often compare observations of the same event by multiple observers, in order to test inter-rater reliability : a measure of reliability that assesses the consistency of observations by different observers.

Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally (Figure 3). Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.

Surveys allow researchers to gather data from larger samples than may be afforded by other research methods . A sample is a subset of individuals selected from a population , which is the overall group of individuals that the researchers are interested in. Researchers study the sample and seek to generalize their findings to the population. Generally, researchers will begin this process by calculating various measures of central tendency from the data they have collected. These measures provide an overall summary of what a typical response looks like. There are three measures of central tendency: mode, median, and mean. The mode is the most frequently occurring response, the median lies at the middle of a given data set, and the mean is the arithmetic average of all data points. Means tend to be most useful in conducting additional analyses like those described below; however, means are very sensitive to the effects of outliers, and so one must be aware of those effects when making assessments of what measures of central tendency tell us about a data set in question.

Figure 3 . Surveys can be administered in a number of ways, including electronically administered research, like the survey shown here. (credit: Robert Nyman)

There is both strength and weakness of the survey in comparison to case studies. By using surveys, we can collect information from a larger sample of people. A larger sample is better able to reflect the actual diversity of the population, thus allowing better generalizability. Therefore, if our sample is sufficiently large and diverse, we can assume that the data we collect from the survey can be generalized to the larger population with more certainty than the information collected through a case study. However, given the greater number of people involved, we are not able to collect the same depth of information on each person that would be collected in a case study.

Another potential weakness of surveys is something we touched on earlier in this module: people don’t always give accurate responses. They may lie, misremember, or answer questions in a way that they think makes them look good. For example, people may report drinking less alcohol than is actually the case.

Any number of research questions can be answered through the use of surveys. One real-world example is the research conducted by Jenkins, Ruppel, Kizer, Yehl, and Griffin (2012) about the backlash against the US Arab-American community following the terrorist attacks of September 11, 2001. Jenkins and colleagues wanted to determine to what extent these negative attitudes toward Arab-Americans still existed nearly a decade after the attacks occurred. In one study, 140 research participants filled out a survey with 10 questions, including questions asking directly about the participant’s overt prejudicial attitudes toward people of various ethnicities. The survey also asked indirect questions about how likely the participant would be to interact with a person of a given ethnicity in a variety of settings (such as, “How likely do you think it is that you would introduce yourself to a person of Arab-American descent?”). The results of the research suggested that participants were unwilling to report prejudicial attitudes toward any ethnic group. However, there were significant differences between their pattern of responses to questions about social interaction with Arab-Americans compared to other ethnic groups: they indicated less willingness for social interaction with Arab-Americans compared to the other ethnic groups. This suggested that the participants harbored subtle forms of prejudice against Arab-Americans, despite their assertions that this was not the case (Jenkins et al., 2012).

Think It Over

A friend of yours is working part-time in a local pet store. Your friend has become increasingly interested in how dogs normally communicate and interact with each other, and is thinking of visiting a local veterinary clinic to see how dogs interact in the waiting room. After reading this section, do you think this is the best way to better understand such interactions? Do you have any suggestions that might result in more valid data?

Contribute!

Improve this page Learn More

• Modification and adaptation. Provided by : Lumen Learning. License : CC BY-SA: Attribution-ShareAlike
• Approaches to Research. Authored by : OpenStax College. Located at : https://openstax.org/books/psychology-2e/pages/2-2-approaches-to-research . License : CC BY: Attribution . License Terms : Download for free at https://openstax.org/books/psychology-2e/pages/1-introduction.
• Descriptive Research. Provided by : Boundless. Located at : https://www.boundless.com/psychology/textbooks/boundless-psychology-textbook/researching-psychology-2/types-of-research-studies-27/descriptive-research-124-12659/ . License : CC BY-SA: Attribution-ShareAlike

Psychological Research

Descriptive Research

Learning objectives.

• Differentiate between descriptive, experimental, and correlational research
• Explain the strengths and weaknesses of case studies, naturalistic observation, and surveys

There are many research methods available to psychologists in their efforts to understand, describe, and explain behavior and the cognitive and biological processes that underlie it. Some methods rely on observational techniques. Other approaches involve interactions between the researcher and the individuals who are being studied—ranging from a series of simple questions to extensive, in-depth interviews—to well-controlled experiments.

The three main categories of psychological research are descriptive, correlational, and experimental research. Research studies that do not test specific relationships between variables are called descriptive, or qualitative, studies . These studies are used to describe general or specific behaviors and attributes that are observed and measured. In the early stages of research it might be difficult to form a hypothesis, especially when there is not any existing literature in the area. In these situations designing an experiment would be premature, as the question of interest is not yet clearly defined as a hypothesis. Often a researcher will begin with a non-experimental approach, such as a descriptive study, to gather more information about the topic before designing an experiment or correlational study to address a specific hypothesis. Descriptive research is distinct from correlational research , in which psychologists formally test whether a relationship exists between two or more variables. Experimental research goes a step further beyond descriptive and correlational research and randomly assigns people to different conditions, using hypothesis testing to make inferences about how these conditions affect behavior. It aims to determine if one variable directly impacts and causes another. Correlational and experimental research both typically use hypothesis testing, whereas descriptive research does not.

Each of these research methods has unique strengths and weaknesses, and each method may only be appropriate for certain types of research questions. For example, studies that rely primarily on observation produce incredible amounts of information, but the ability to apply this information to the larger population is somewhat limited because of small sample sizes. Survey research, on the other hand, allows researchers to easily collect data from relatively large samples. While this allows for results to be generalized to the larger population more easily, the information that can be collected on any given survey is somewhat limited and subject to problems associated with any type of self-reported data. Some researchers conduct archival research by using existing records. While this can be a fairly inexpensive way to collect data that can provide insight into a number of research questions, researchers using this approach have no control on how or what kind of data was collected.

Correlational research can find a relationship between two variables, but the only way a researcher can claim that the relationship between the variables is cause and effect is to perform an experiment. In experimental research, which will be discussed later in the text, there is a tremendous amount of control over variables of interest. While this is a powerful approach, experiments are often conducted in very artificial settings. This calls into question the validity of experimental findings with regard to how they would apply in real-world settings. In addition, many of the questions that psychologists would like to answer cannot be pursued through experimental research because of ethical concerns.

The three main types of descriptive studies are case studies, naturalistic observation, and surveys.

Case Studies

In 2011, the New York Times published a feature story on Krista and Tatiana Hogan, Canadian twin girls. These particular twins are unique because Krista and Tatiana are conjoined twins, connected at the head. There is evidence that the two girls are connected in a part of the brain called the thalamus, which is a major sensory relay center. Most incoming sensory information is sent through the thalamus before reaching higher regions of the cerebral cortex for processing.

Link to Learning

To learn more about Krista and Tatiana, watch this video about their lives as conjoined twins.

The implications of this potential connection mean that it might be possible for one twin to experience the sensations of the other twin. For instance, if Krista is watching a particularly funny television program, Tatiana might smile or laugh even if she is not watching the program. This particular possibility has piqued the interest of many neuroscientists who seek to understand how the brain uses sensory information.

These twins represent an enormous resource in the study of the brain, and since their condition is very rare, it is likely that as long as their family agrees, scientists will follow these girls very closely throughout their lives to gain as much information as possible (Dominus, 2011).

In observational research, scientists are conducting a clinical or case study when they focus on one person or just a few individuals. Indeed, some scientists spend their entire careers studying just 10–20 individuals. Why would they do this? Obviously, when they focus their attention on a very small number of people, they can gain a tremendous amount of insight into those cases. The richness of information that is collected in clinical or case studies is unmatched by any other single research method. This allows the researcher to have a very deep understanding of the individuals and the particular phenomenon being studied.

If clinical or case studies provide so much information, why are they not more frequent among researchers? As it turns out, the major benefit of this particular approach is also a weakness. As mentioned earlier, this approach is often used when studying individuals who are interesting to researchers because they have a rare characteristic. Therefore, the individuals who serve as the focus of case studies are not like most other people. If scientists ultimately want to explain all behavior, focusing attention on such a special group of people can make it difficult to generalize any observations to the larger population as a whole. Generalizing refers to the ability to apply the findings of a particular research project to larger segments of society. Again, case studies provide enormous amounts of information, but since the cases are so specific, the potential to apply what’s learned to the average person may be very limited.

Naturalistic Observation

If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances are that almost everyone in the classroom will raise their hand, but do you think hand washing after every trip to the restroom is really that universal?

This is very similar to the phenomenon mentioned earlier in this module: many individuals do not feel comfortable answering a question honestly. But if we are committed to finding out the facts about hand washing, we have other options available to us.

Suppose we send a classmate into the restroom to actually watch whether everyone washes their hands after using the restroom. Will our observer blend into the restroom environment by wearing a white lab coat, sitting with a clipboard, and staring at the sinks? We want our researcher to be inconspicuous—perhaps standing at one of the sinks pretending to put in contact lenses while secretly recording the relevant information. This type of observational study is called naturalistic observation : observing behavior in its natural setting. To better understand peer exclusion, Suzanne Fanger collaborated with colleagues at the University of Texas to observe the behavior of preschool children on a playground. How did the observers remain inconspicuous over the duration of the study? They equipped a few of the children with wireless microphones (which the children quickly forgot about) and observed while taking notes from a distance. Also, the children in that particular preschool (a “laboratory preschool”) were accustomed to having observers on the playground (Fanger, Frankel, & Hazen, 2012).

It is critical that the observer be as unobtrusive and as inconspicuous as possible: when people know they are being watched, they are less likely to behave naturally. If you have any doubt about this, ask yourself how your driving behavior might differ in two situations: In the first situation, you are driving down a deserted highway during the middle of the day; in the second situation, you are being followed by a police car down the same deserted highway (Figure 1).

It should be pointed out that naturalistic observation is not limited to research involving humans. Indeed, some of the best-known examples of naturalistic observation involve researchers going into the field to observe various kinds of animals in their own environments. As with human studies, the researchers maintain their distance and avoid interfering with the animal subjects so as not to influence their natural behaviors. Scientists have used this technique to study social hierarchies and interactions among animals ranging from ground squirrels to gorillas. The information provided by these studies is invaluable in understanding how those animals organize socially and communicate with one another. The anthropologist Jane Goodall, for example, spent nearly five decades observing the behavior of chimpanzees in Africa (Figure 2). As an illustration of the types of concerns that a researcher might encounter in naturalistic observation, some scientists criticized Goodall for giving the chimps names instead of referring to them by numbers—using names was thought to undermine the emotional detachment required for the objectivity of the study (McKie, 2010).

The greatest benefit of naturalistic observation is the validity, or accuracy, of information collected unobtrusively in a natural setting. Having individuals behave as they normally would in a given situation means that we have a higher degree of ecological validity, or realism, than we might achieve with other research approaches. Therefore, our ability to generalize the findings of the research to real-world situations is enhanced. If done correctly, we need not worry about people or animals modifying their behavior simply because they are being observed. Sometimes, people may assume that reality programs give us a glimpse into authentic human behavior. However, the principle of inconspicuous observation is violated as reality stars are followed by camera crews and are interviewed on camera for personal confessionals. Given that environment, we must doubt how natural and realistic their behaviors are.

The major downside of naturalistic observation is that they are often difficult to set up and control. In our restroom study, what if you stood in the restroom all day prepared to record people’s hand washing behavior and no one came in? Or, what if you have been closely observing a troop of gorillas for weeks only to find that they migrated to a new place while you were sleeping in your tent? The benefit of realistic data comes at a cost. As a researcher you have no control of when (or if) you have behavior to observe. In addition, this type of observational research often requires significant investments of time, money, and a good dose of luck.

Sometimes studies involve structured observation. In these cases, people are observed while engaging in set, specific tasks. An excellent example of structured observation comes from Strange Situation by Mary Ainsworth (you will read more about this in the module on lifespan development). The Strange Situation is a procedure used to evaluate attachment styles that exist between an infant and caregiver. In this scenario, caregivers bring their infants into a room filled with toys. The Strange Situation involves a number of phases, including a stranger coming into the room, the caregiver leaving the room, and the caregiver’s return to the room. The infant’s behavior is closely monitored at each phase, but it is the behavior of the infant upon being reunited with the caregiver that is most telling in terms of characterizing the infant’s attachment style with the caregiver.

Another potential problem in observational research is observer bias . Generally, people who act as observers are closely involved in the research project and may unconsciously skew their observations to fit their research goals or expectations. To protect against this type of bias, researchers should have clear criteria established for the types of behaviors recorded and how those behaviors should be classified. In addition, researchers often compare observations of the same event by multiple observers, in order to test inter-rater reliability : a measure of reliability that assesses the consistency of observations by different observers.

Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally (Figure 3). Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.

Surveys allow researchers to gather data from larger samples than may be afforded by other research methods . A sample is a subset of individuals selected from a population , which is the overall group of individuals that the researchers are interested in. Researchers study the sample and seek to generalize their findings to the population.

There is both strength and weakness of the survey in comparison to case studies. By using surveys, we can collect information from a larger sample of people. A larger sample is better able to reflect the actual diversity of the population, thus allowing better generalizability. Therefore, if our sample is sufficiently large and diverse, we can assume that the data we collect from the survey can be generalized to the larger population with more certainty than the information collected through a case study. However, given the greater number of people involved, we are not able to collect the same depth of information on each person that would be collected in a case study.

Another potential weakness of surveys is something we touched on earlier in this module: people don’t always give accurate responses. They may lie, misremember, or answer questions in a way that they think makes them look good. For example, people may report drinking less alcohol than is actually the case.

Any number of research questions can be answered through the use of surveys. One real-world example is the research conducted by Jenkins, Ruppel, Kizer, Yehl, and Griffin (2012) about the backlash against the US Arab-American community following the terrorist attacks of September 11, 2001. Jenkins and colleagues wanted to determine to what extent these negative attitudes toward Arab-Americans still existed nearly a decade after the attacks occurred. In one study, 140 research participants filled out a survey with 10 questions, including questions asking directly about the participant’s overt prejudicial attitudes toward people of various ethnicities. The survey also asked indirect questions about how likely the participant would be to interact with a person of a given ethnicity in a variety of settings (such as, “How likely do you think it is that you would introduce yourself to a person of Arab-American descent?”). The results of the research suggested that participants were unwilling to report prejudicial attitudes toward any ethnic group. However, there were significant differences between their pattern of responses to questions about social interaction with Arab-Americans compared to other ethnic groups: they indicated less willingness for social interaction with Arab-Americans compared to the other ethnic groups. This suggested that the participants harbored subtle forms of prejudice against Arab-Americans, despite their assertions that this was not the case (Jenkins et al., 2012).

Think It Over

A friend of yours is working part-time in a local pet store. Your friend has become increasingly interested in how dogs normally communicate and interact with each other, and is thinking of visiting a local veterinary clinic to see how dogs interact in the waiting room. After reading this section, do you think this is the best way to better understand such interactions? Do you have any suggestions that might result in more valid data?

CC licensed content, Original

• Modification and adaptation. Provided by : Lumen Learning. License : CC BY-SA: Attribution-ShareAlike

CC licensed content, Shared previously

• Approaches to Research. Authored by : OpenStax College. Located at : https://openstax.org/books/psychology-2e/pages/2-2-approaches-to-research . License : CC BY: Attribution . License Terms : Download for free at https://openstax.org/books/psychology-2e/pages/1-introduction.
• Descriptive Research. Provided by : Boundless. Located at : https://www.boundless.com/psychology/textbooks/boundless-psychology-textbook/researching-psychology-2/types-of-research-studies-27/descriptive-research-124-12659/ . License : CC BY-SA: Attribution-ShareAlike

research studies that do not test specific relationships between variables; they are used to describe general or specific behaviors and attributes that are observed and measured

tests whether a relationship exists between two or more variables

tests a hypothesis to determine cause and effect relationships

observational research study focusing on one or a few people

observation of behavior in its natural setting

inferring that the results for a sample apply to the larger population

when observations may be skewed to align with observer expectations

measure of agreement among observers on how they record and classify a particular event

list of questions to be answered by research participants—given as paper-and-pencil questionnaires, administered electronically, or conducted verbally—allowing researchers to collect data from a large number of people

the collection of individuals on which we collect data.

a larger collection of individuals that we would like to generalize our results to.

General Psychology Copyright © by OpenStax and Lumen Learning is licensed under a Creative Commons Attribution 4.0 International License , except where otherwise noted.

Share This Book

• Augmentation therapy for depression study
• The STAR*D study in depression
• The COMBINE Study in alcoholism
• The Health and Retirement Study
• Serotonin transport study in mother-infant pairs
• Meta-analysis of clinical trials in schizophrenia
• Human laboratory study of menthol’s effects on nicotine reinforcement in smokers
• fMRI study of working memory in schizophrenia
• Association between unemployment and depression
• Mediation analyses from Chapter 9
• Power calculations from Chapter 11
• Raw and adjusted p-values from Chapter 6
• Publications

INFORMATION FOR

• Residents & Fellows
• Researchers

Three YSM Faculty Win Awards to Support Research in Aging, Geroscience

Three Yale School of Medicine professors are among the winners of the American Federation for Aging Research New Investigators Awards in Aging and Biology Geroscience Research. The winners each receive a three-year award totaling $375,000 to support their research into aging or biology geroscience.

AFAR announced the Second Cohort of the Hevolution/American Federation for Aging Research New Investigators Awardees in Aging and Biology Geroscience Research. The YSM faculty members are Caitlin Davis, PhD, Assistant Professor of Chemistry, Dan Jane-wit, MD, PhD, Associate Professor of Medicine (Cardiology) and Immunology, and Siyuan (Steven) Wang, PhD, Associate Professor of Genetics and Cell Biology. They are among 18 winners AFAR announced on April 26.

The Hevolution Foundation and AFAR provide the awards to junior investigators (MDs and/or PhDs) with at least three years of independent research who conduct research projects in basic biology of aging or geroscience . The program provides flexible support for research projects in basic biology of aging, as well as geroscience (projects that translate advances in basic research on aging biology from the laboratory to the clinic.)

The award will support Dr. Davis and her study on “Spatiotemporal Rewiring of Lipid Metabolism in Aging Tissues.” Dr. Davis is investigating biological hallmarks of aging in lipid metabolism. Aging is associated with a shift of metabolism towards lipogenesis. Therefore, understanding the dynamics of competing lipogenic pathways across the cell, their variations across cell types, and their responses to cellular stresses is crucial. However, measuring lipid metabolism inside the cell is not trivial. Using state-of-the-art infrared microscopy, this project investigates the spatial distribution, metabolic rates, and stress response of competing lipogenic pathways in aging fat and liver cells.

Dr. Jane-wit is studying “Complement Protein Aggregates in Age-Related Amyloidosis.” While the root causes of aging are unknown, protein aggregates are thought to have harmful effects. During aging, proteins become misfolded, forming aggregates that cause inflammation. Understanding which protein(s) become aggregated holds the promise of new therapies promoting healthy aging. Membrane attack complexes (MACs) are immune proteins long believed to contribute to aging via cell death. Work in Dr. Jane-wit’s laboratory surprisingly found that MAC proteins formed aggregates causing inflammation without cell death. Using innovative molecular tools and genetically-engineered mouse models, Dr. Jane-Wit will test a new concept that MAC aggregates promote age-related inflammation and decline in physiologic function.

Dr. Wang is studying, “Developing a High-Content Spatial Transcriptomic Screen Method to Discover Novel Regulators of Cell-Cell Interaction in the Native Senescent Microenvironment.” A fundamental question in the biology of aging revolves around understanding how different cell types and cell states change and interact to collectively contribute to the aging phenotype. This has been difficult to address as the aging process is not uniform across tissues and organs. In an aging tissue, a cell's position can be as pivotal as its inherent properties in shaping tissue function during aging. Recent breakthroughs in single-cell spatial omic technologies have significantly advanced our understanding of molecular and cellular organizations within tissues but cannot unveil direct functional mechanisms or causative factors. In this pioneering project, Dr. Wang aims to develop an in vivo genome-wide screening technology for identifying spatial transcriptome regulators in aging tissue, marking a new frontier in aging research. These identified regulators could be targeted to modify the spatial transcriptome associated with aging, fostering healthier aging by modulating spatial communication between relevant cell types.

Featured in this article

• Caitlin Davis, PhD Assistant Professor
• Daniel Jane-Wit, MD/PhD Associate Professor of Medicine (Cardiology) and Immunobiology
• Siyuan (Steven) Wang, PhD Associate Professor of Genetics and Cell Biology

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

424 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• HHS Author Manuscripts

Qualitative Descriptive Methods in Health Science Research

Karen jiggins colorafi.

1 College of Nursing & Health Innovation, Arizona State University, Phoenix, AZ, USA

Bronwynne Evans

The purpose of this methodology paper is to describe an approach to qualitative design known as qualitative descriptive that is well suited to junior health sciences researchers because it can be used with a variety of theoretical approaches, sampling techniques, and data collection strategies.

Background:

It is often difficult for junior qualitative researchers to pull together the tools and resources they need to embark on a high-quality qualitative research study and to manage the volumes of data they collect during qualitative studies. This paper seeks to pull together much needed resources and provide an overview of methods.

A step-by-step guide to planning a qualitative descriptive study and analyzing the data is provided, utilizing exemplars from the authors’ research.

This paper presents steps to conducting a qualitative descriptive study under the following headings: describing the qualitative descriptive approach, designing a qualitative descriptive study, steps to data analysis, and ensuring rigor of findings.

Conclusions:

The qualitative descriptive approach results in a summary in everyday, factual language that facilitates understanding of a selected phenomenon across disciplines of health science researchers.

There is an explosion in qualitative methodologies among health science researchers because social problems lend themselves toward thoughtful exploration, such as when issues of interest are complex, have variables or concepts that are not easily measured, or involve listening to populations who have traditionally been silenced ( Creswell, 2013 ). Creswell (2013 , p. 48) suggests qualitative research is preferred when health science researchers seek to (a) share individual stories, (b) write in a literary, flexible style, (c) understand the context or setting of issues, (d) explain mechanisms or linkages in causal theories, (e) develop theories, and (f) when traditional quantitative statistical analyses do not fit the problem at hand. Typically, qualitative textbooks present learners with five approaches for qualitative inquiry: narrative, phenomenological, grounded theory, case study, and ethnography. Yet eminent researcher Margarete Sandelowski argues that in “the now vast qualitative methods literature, there is no comprehensive description of qualitative description as a distinctive method of equal standing with other qualitative methods, although it is one of the most frequently employed methodological approaches in the practice disciplines” ( Sandelowski, 2000 ). Qualitative description is especially amenable to health environments research because it provides factual responses to questions about how people feel about a particular space, what reasons they have for using features of the space, who is using particular services or functions of a space, and the factors that facilitate or hinder use.

The purpose of this methodology article is to define and outline qualitative description for health science researchers, providing a starter guide containing important primary sources for those who wish to become better acquainted with this methodological approach.

Describing the Qualitative Descriptive Approach

In two seminal articles, Sandelowski promotes the mainstream use of qualitative description ( Sandelowski, 2000 , 2010 ) as a well-developed but unacknowledged method which provides a “comprehensive summary of an event in the every day terms of those events” ( Sandelowski, 2000 , p. 336). Such studies are characterized by lower levels of interpretation than are high-inference qualitative approaches such as phenomenology or grounded theory and require a less “conceptual or otherwise highly abstract rendering of data” ( Sandelowski, 2000 , p. 335). Researchers using qualitative description “stay closer to their data and to the surface of words and events” ( Sandelowski, 2000 , p. 336) than many other methodological approaches. Qualitative descriptive studies focus on low-inference description, which increases the likelihood of agreement among multiple researchers. The difference between high and low inference approaches is not one of rigor but refers to the amount of logical reasoning required to move from a data-based premise to a conclusion. Researchers who use qualitative description may choose to use the lens of an associated interpretive theory or conceptual framework to guide their studies, but they are prepared to alter that framework as necessary during the course of the study ( Sandelowski, 2010 ). These theories and frameworks serve as conceptual hooks upon which hang study procedures, analysis, and re-presentation. Findings are presented in straightforward language that clearly describes the phenomena of interest.

Other cardinal features of the qualitative descriptive approach include (a) a broad range of choices for theoretical or philosophical orientations, (b) the use of virtually any purposive sampling technique (e.g., maximum variation, homogenous, typical case, criterion), (c) the use of observations, document review, or minimally to moderately structured interview or focus group questions, (d) content analysis and descriptive statistical analysis as data analysis techniques, and (e) the provision of a descriptive summary of the informational contents of the data organized in a way that best fits the data ( Neergaard, Olesen, Andersen, & Sondergaard, 2009 ; Sandelowski, 2000 , 2001 , 2010 ).

Designing a Qualitative Descriptive Study

Methodology.

Unlike traditional qualitative methodologies such as grounded theory, which are built upon a particular, prescribed constellation of procedures and techniques, qualitative description is grounded in the general principles of naturalistic inquiry. Lincoln and Guba suggest that naturalistic inquiry deals with the concept of truth, whereby truth is “a systematic set of beliefs, together with their accompanying methods” ( Lincoln & Guba, 1985 , p. 16). Using an often eclectic compilation of sampling, data collection, and data analysis techniques, the researcher studies something in its natural state and does not attempt to manipulate or interfere with the ordinary unfolding of events. Taken together, these practices lead to “true understanding” or “ultimate truth.” Table 1 describes design elements in two exemplar qualitative descriptive studies and serves as guide to the following discussion.

Example of Study Design Elements for Two Studies.

Theoretical Framework

Theoretical frameworks serve as organizing structures for research design: sampling, data collection, analysis, and interpretation, including coding schemes, and formatting hypothesis for further testing ( Evans, Coon, & Ume, 2011 ; Miles, Huberman, & Saldana, 2014 ; Sandelowski, 2010 ). Such frameworks affect the way in which data are ultimately viewed; qualitative description supports and allows for the use of virtually any theory ( Sandelowski, 2010 ). Creswell’s chapter on “Philosophical Assumptions and Interpretative Frameworks” (2013) is a useful place to gain understanding about how to embed a theory into a study.

Sampling choices place a boundary around the conclusions you can draw from your qualitative study and influence the confidence you and others place in them ( Miles et al., 2014 ). A hallmark of the qualitative descriptive approach is the acceptability of virtually any sampling technique (e.g., maximum variation where you aim to collect as many different cases as possible or homogenous whereby participants are mostly the same). See Miles, Huberman, and Saldana’s (2014 , p. 30) “Bounding the Collection of Data” discussion to select an appropriate and congruent purposive sampling strategy for your qualitative study.

Data Collection

In qualitative descriptive studies, data collection attempts to discover “the who, what and where of events” or experiences ( Sandelowski, 2000 , p.339). This includes, but is not limited to focus groups, individual interviews, observation, and the examination of documents or artifacts.

Data Analysis

Content analysis refers to a technique commonly used in qualitative research to analyze words or phrases in text documents. Hsieh and Shannon (2005) present three types of content analysis, any of which could be used in a qualitative descriptive study. Conventional content analysis is used in studies that aim to describe a phenomenon where exiting research and theory are limited. Data are collected from open-ended questions, read word for word, and then coded. Notes are made and codes are categorized. Directed content analysis is used in studies where existing theory or research exists: it can be used to further describe phenomena that are incomplete or would benefit from further description. Initial codes are created from theory or research and applied to data and unlabeled portions of text are given new codes. Summative content analysis is used to quantify and interpret words in context, exploring their usage. Data sources are typically seminal texts or electronic word searches.

Quantitative data can be included in qualitative descriptive studies if they aim to more adequately or fully describe the participants or phenomenon of interest. Counting is conceptualized as a “means to and end, not the end itself” by Sandelowski (2000 , p. 338) who emphasizes that careful descriptive statistical analysis is an effort to understand the content of data, not simply the means and frequencies, and results in a highly nuanced description of the patterns or regularities of the phenomenon of interest ( Sandelowski, 2000 , 2010 ). The use of validated measures can assist with generating dependable and meaningful findings, especially when the instrument (e.g., survey, questionnaire, or list of questions) used in your study has been used in others, helping to build theory, improve predictions, or make recommendations ( Miles et al., 2014 ).

Data Re-Presentation

In clear and simple terms, the “expected outcome of qualitative descriptive studies is a straight forward descriptive summary of the informational contents of data organized in a way that best fits the data” ( Sandelowski, 2000 , p. 339). Data re-presentation techniques allow for tremendous creativity and variation among researchers and studies. Several good resources are provided to spur imagination ( Miles et al., 2014 ; Munhall & Chenail, 2008 ; Wolcott, 2009 ).

Steps to Data Analysis

It is often difficult for junior health science researchers to know what to do with the volumes of data collected during a qualitative study and formal course work in traditional qualitative methods courses are typically sparse regarding the specifics of data management. It is for those reasons that this section of our article will provide a detailed description of the data analysis techniques used in qualitative descriptive methodology. The following steps are case examples of a study undertaken by one author (K.J.C.) after completing a data management course offered by another author (B.E.). Examples are offered from the two studies noted in Table 1 . It is offered in list format for general readability, but the qualitative researcher should recognize that qualitative analyses are iterative and recursive by nature.

Example of a Coding Manual.

Note . SES = socioeconomic status.

Reading from the left in Table 2 , codes were given a number and letter for use in marking sections of text. Next, the code name indicating a theme was entered in boldface type with a definition in the code immediately under it. The second column provided an exemplar of each code, along with a notation indicating where it was found in the data, so that coders could recognize instances of that particular code when they saw them.

The coding manual was tested against data gathered in a preliminary study and was revised as codes found to overlap or be missing entirely. We continued to revise it iteratively during the study as data collection and analysis proceeded and then used it to recode previously coded data. Using this procedure, it was used to revisit the data several times.

• Each transcribed document was formatted with wide right margins that allowed the investigator to apply codes and generate marginal remarks by hand. Marginal remarks are handwritten comments entered by the investigator. They represent an attempt to stay “alert” about analysis, forming ideas and recording reactions to the meaning of what is seen in the data. Marginal remarks often suggest new interpretations, leads, and connections or distinctions with other parts of the data ( Miles et al., 2014 ). Such remarks are preanalytic and add meaning and clarity to transcripts.

Level 1 Coding With Meaning Units.

• Conceptually similar codes were organized into categories (coding groups of coded themes that were increasingly abstract) through revisiting the theory framing the study (asking, “does this system of coding make sense according to the chosen theory?”). Miles et al. (2014) provide many examples for creating, categorizing, and revising codes, including highlighting a technique used by Corbin and Strauss ( Corbin & Strauss, 2015 ) that includes growing a list of codes and then applying a slightly more abstract label to the code, creating new categories of codes with each revision. This is often referred to as second-level or pattern coding, a way of grouping data into a smaller number of sets, themes, or constructs. During the analysis of data, patterns were generated and the researcher spent significant amounts of time with different categorizations, asking questions, checking relationships, and generally resisting the urge to be “locked too quickly into naming a pattern” ( Miles et al., 2014 , p. 69).
• During this phase of analysis, pattern codes were revised and redefined in the coding manual and exemplars were used to clarify the understanding of each code. Miles et al. (2014) suggest that software can be helpful during this categorization (counting) step, so lists of observed engagement behaviors were also recorded in Dedoose software ( Dedoose, 2015 ) by code so that frequencies could be captured and analyzed. Despite the assistance of Dedoose, the researcher found that hand sorting codes into themes and categories was best done on paper.

Example of an analytic memo used in qualitative description analysis.

Data Matrix.

Note . The CLOX is an executive clock drawing task that tests cognition and was used in this study with the caregiver (CG) and the care recipient (CR). The CG Strain and the CG Gain scores were derived by the researcher through a qualitative content analysis ( Evans, Coon, & Belyea, 2006 ).

• Finally, the data are re-presented in a creative but rigorous way that are judged to best fit the findings ( Miles et al., 2014 ; Sandelowski & Leeman, 2012 ; Stake, 2010 ; Wolcott, 2009 ).

Strategies for Ensuring Rigor of Findings

Many qualitative researchers do not provide enough information in their reports about the analytic strategies used to ensure verisimilitude or the “ring of truth” for the conclusions. Miles, Huberman, and Saldana (2014) outline 13 tactics for generating meaning from data and another 13 for testing or confirming findings. They also provide five standards for assessing the quality of conclusions. The techniques relied upon most heavily during a qualitative descriptive study ought to be addressed within the research report. It is important to establish “trustworthiness” and “authenticity” in qualitative research that are similar to the terms validity and reliability in quantitative research. The five standards (objectivity, dependability, credibility, transferability, and application) typically used in qualitative descriptive studies to assess quality and legitimacy (trustworthiness and authenticity) of the conclusions are discussed in the next sections ( Lincoln & Guba, 1985 ; Miles et al., 2014 ).

Objectivity

First, objectivity (confirmability) is conceptualized as relative neutrality and reasonable freedom from researcher bias and can be addressed by (a) describing the study’s methods and procedures in explicit detail, (b) sharing the sequence of data collection, analysis, and presentation methods to create an audit trail, (c) being aware of and reporting personal assumptions and potential bias, (d) retaining study data and making it available to collaborators for evaluation.

Dependability

Second, dependability (reliability or auditability) can be fostered by consistency in procedures across participants over time through various methods, including the use of semistructured interview questions and an observation data collection worksheet. Quality control ( Miles et al., 2014 ) can be fostered by:

• deriving study procedures from clearly outlined research questions and conceptual theory, so that data analysis could be linked back to theoretical constructs;
• clearly describing the investigator’s role and status at the research site;
• demonstrating parallelism in findings across sources (i.e., interview vs. observation, etc.);
• triangulation through the use of observations, interviews, and standardized measures to more adequately describe various characteristics of the sample population ( Denzin & Lincoln, 1994 );
• demonstrating consistency in data collection for all participants (i.e., using the same investigator and preprinted worksheets, asking the same questions in the same order);
• developing interview questions and observation techniques based on theory, revised, and tested during preliminary work;
• developing a coding manual a priori to guide data analysis, containing a “start list” of codes derived from the theoretical framework and relevant literature ( Fonteyn et al., 2008 ; Hsieh & Shannon, 2005 ; Miles et al., 2014 ); and
• developing a monitoring plan (fidelity) to ensure that junior researchers, especially do not go “beyond the data” ( Sandelowski, 2000 ) in interpretation. In keeping with the qualitative tradition, data analysis and collection should occur simultaneously, giving the investigator the opportunity to correct errors or make revisions.

Credibility

Third, credibility or verisimilitude (internal validity) is defined as the truth value of data: Do the findings of the study make sense ( Miles et al., 2014 , p. 312). Credibility in qualitative work promotes descriptive and evaluative understanding, which can be addressed by (a) providing context-rich “thick descriptions,” that is, the work of interpretation based on data ( Sandelowski, 2004 ), (b) checking with other practitioners or researchers that the findings “ring true,” (c) providing a comprehensive account, (d) using triangulation strategies, (e) searching for negative evidence, and (f) linking findings to a theoretical framework.

Transferability

Fourth, transferability (external validity or “fittingness”) speaks to whether the findings of your study have larger import and application to other settings or studies. This includes a discussion of generalizability. Sample to population generalizability is important to quantitative researchers and less helpful to qualitative researchers who seek more of an analytic or case-to-case transfer ( Miles et al., 2014 ). Nonetheless, transferability can be aided by (a) describing the characteristics of the participants fully so that comparisons with other groups may be made, (b) adequately describing potential threats to generalizability through sample and setting sections, (c) using theoretical sampling, (d) presenting findings that are congruent with theory, and (e) suggesting ways that findings from your study could be tested further by other researchers.

Application

Finally, Miles et al. (2014) speak to the utilization, application, or action orientation of the data. “Even if we know that a study’s findings are valid and transferable,” they write, “we still need to know what the study does for its participants and its consumers” ( Miles et al., 2014 , p. 314). To address application, findings of qualitative descriptive studies are typically made accessible to potential consumers of information through the publication of manuscripts, poster presentations, and summary reports written for consumers. In addition, qualitative descriptive study findings may stimulate further research, promote policy discussions, or suggest actual changes to a product or environment.

Implications for Practice

The qualitative description clarified and advocated by Sandelowski (2000 , 2010 ) is an excellent methodological choice for the healthcare environments designer, practitioner, or health sciences researcher because it provides rich descriptive content from the subjects’ perspective. Qualitative description allows the investigator to select from any number of theoretical frameworks, sampling strategies, and data collection techniques. The various content analysis strategies described in this paper serve to introduce the investigator to methods for data analysis that promote staying “close” to the data, thereby avoiding high-inference techniques likely challenging to the novice investigator. Finally, the devotion to thick description (interpretation based on data) and flexibility in the re-presentation of study findings is likely to produce meaningful information to designers and healthcare leaders. The practical, step-by-step nature of this article should serve as a starting guide to researchers interested in this technique as a way to answer their own burning questions.

Acknowledgments

The author would like to recognize the other members of her dissertation committee for their contributions to the study: Gerri Lamb, Karen Dorman Marek, and Robert Greenes.

The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: Research assistance for data analysis and manuscript development was supported by training funds from the National Institutes of Health/National Institute on Nursing Research (NIH/NINR), award T32 1T32NR012718-01 Transdisciplinary Training in Health Disparities Science (C. Keller, P.I.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH or the NINR. This research was supported through the Hartford Center of Gerontological Nursing Excellence at Arizona State University College of Nursing & Health Innovation.

Declaration of Conflicting Interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

• Corbin J, & Strauss A (2015). Basics of qualitative research: Techniques and procedures for developing grounded theory (4th ed.). Thousand Oaks, CA: Sage. [ Google Scholar ]
• Creswell J (2013). Qualitative inquiry and research design: Choosing among five approaches (3rd ed.). Los Angeles, CA: Sage. [ Google Scholar ]
• Creswell J, & Plano-Clark V (2007). Designing and conducting mixed methods research . Thousand Oaks, CA: Sage. [ Google Scholar ]
• Dedoose. (2015). Version 6.1.18, web application for managing, analyzing, and presenting qualitative and mixed method research data Los Angeles, CA: SocioCultural Research Consultants, LLC; Retrieved from www.dedoose.com [ Google Scholar ]
• Denzin N, & Lincoln Y (1994). The handbook of qualitative research . New York, NY: Sage. [ Google Scholar ]
• Denzin N, Lincoln Y, & Giardina M (2006). Disciplining qualitative research . International Journal of Qualitative Studies in Education , 19 , 769–782. [ Google Scholar ]
• Evans BC, Belyea MJ, Coon DW, & Ume E (2012). Activities of daily living in Mexican American caregivers: The key to continuing informal care . Journal of Family Nursing , 18 , 439–466. doi:410.1177/1074840712450210. Epub 1074840 712452012 Jun 1074840712450226 [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Evans BC, Belyea MJ, & Ume E (2011). Mexican-American males providing personal care for their mothers . Hispanic Journal of Behavioral Sciences , 33 , 234–260. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Evans B, Coon D, & Belyea M (2006). Worry among Mexican American caregivers of community-dwelling elders . Public Health Nursing , 23 ( 3 ), 284–291. doi: 10.1111/j.1525-1446.2006.230312.x [ CrossRef ] [ Google Scholar ]
• Evans BC, Coon DW, & Ume E (2011). Use of theoretical frameworks as a pragmatic guide for mixed methods studies: A methodological necessity? Journal of Mixed Methods Research , 5 , 276–292. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Fonteyn ME, Vettese M, Lancaster DR, & Bauer-Wu S (2008). Developing a codebook to guide content analysis of expressive writing transcripts . Applied Nursing Research , 21 , 165–168. doi: 10.1016/j.apnr.2006.08.005 [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Hsieh H, & Shannon S (2005). Three approaches to qualitative content analysis . Qualitative Health Research , 15 , 1277–1288. [ PubMed ] [ Google Scholar ]
• Jiggins Colorafi K (2015). Patient centered health information technology: Engagement with the plan of care among older adults with multi-morbidities . Retrieved from ProQuest. [ Google Scholar ]
• Lincoln Y, & Guba E (1985). Naturalistic inquiry . New York, NY: Sage. [ Google Scholar ]
• Miles M, Huberman M, & Saldana J (2014). Qualitative data analysis: A methods sourcebook (3rd ed.). Thousand Oaks, CA: Sage. [ Google Scholar ]
• Munhall P, & Chenail R (2008). Qualitative research proposals and reports: A guide (3rd ed.). Boston, MA: Jones and Bartlett. [ Google Scholar ]
• Neergaard MA, Olesen F, Andersen RS, & Sondergaard J (2009). Qualitative description - the poor cousin of health research? BMC Medical Research Methodology , 9 , 52. doi: 10.1186/1471-2288-9-52 [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Sandelowski M (2000). Whatever happened to qualitative description? Research in Nursing & Health , 23 , 334–340. [ PubMed ] [ Google Scholar ]
• Sandelowski M (2001). Focus on research methods. Real qualitative researchers do not count: The use of numbers in qualitative research . Research in Nursing & Health , 24 , 230–240. [ PubMed ] [ Google Scholar ]
• Sandelowski M (2004). Counting cats in Zanzibar . Research in Nursing & Health , 27 , 215–216. [ PubMed ] [ Google Scholar ]
• Sandelowski M (2010). What’s in a name? Qualitative description revisited . Research in Nursing & Health , 33 , 77–84. doi: 10.1002/nur.20362 [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Sandelowski M, & Leeman J (2012). Writing usable qualitative health research findings . Qualitative Health Research , 22 , 1404–1413. [ PubMed ] [ Google Scholar ]
• Spradley J (1980). Patricipant observation . Belmont, CA: Wadsworth Cengage Learning. [ Google Scholar ]
• Stake R (2010). Qualitative research: Studying how things work . New York, NY: The Guilford Press. [ Google Scholar ]
• Wolcott H (2009). Writing up qualitative research (3rd ed.). Los Angeles, CA: Sage. [ Google Scholar ]