Let’s say you’re setting out to research what makes people happy. You’ve read the previous chapter, so you know the importance of defining your concepts. You’ve done that, and decided that the best way to understand how happy people are is to have them rate their level of happiness on a scale of 0-10. Great, but how are you going to get people to give you that information?
One way would be with a survey. A survey involves collecting data from a group of people by administering a standardized questionnaire. The questionnaire, or survey can be written documentation that is administered either in person (door-to-door), on paper (through the mail), by phone, or online. Survey research is a quantitative method that uses predetermined questions that aim to describe or explain features of a very large group or groups.
Surveys are really common. The way we know how many people are in the United States is based on a survey (US Census). How do we know the unemployment rate in the United States? A survey. How do TV stations call the election as soon as polls close, before 98% of ballots have been counted? Surveys.
In this chapter I’ll try to walk you through the steps of developing a survey project. Let’s jump to the conclusion though, to make sure that we’re all on the same page. Below is a portion of a survey. It’s not the whole thing, just a few of the questions included on that survey. But that’s a survey, a form that asks respondents set questions and provides them space to answer them. There’s lots of ways you can deliver the survey, there’s a limitless number of questions you can ask, and you’ll still have to figure out who you’re going to survey. But that’s the end goal.
We’re going to talk about a lot of minutiae in this chapter, but it’s all important to doing a good survey.
The reason that researchers and society rely on surveys is because of their ability to provide information, even for people not asked to provide data. If you’re developing your happiness survey, are you going to gather the information from all 8 billion people on the planet? Imagine trying to get data about everyone just in your own neighborhood. That would be a challenge, to put it kindly. Luckily, you don’t have to. Researchers have developed ways to understand everyone based on the characteristics of a few .
Surveys, if correctly developed, can provide reliable information that can be generalized to the population. Generalizability means that what we learn from the sample (53% of the respondents like vanilla ice cream) can be related to everyone (53% of people likes vanilla ice cream). To formulate projections or broad-based conclusions, you need to conduct surveys that represent the public at large, which means including relevant groups (based on race, gender, age group, etc.) from a larger population in the correct proportions. We’ll talk more about populations and samples in a future chapter, but it’s worth knowing what’s possible.
Because of the ability to generalize the information we gather, surveys are often a cost effective form of research. The physical production of a survey questionnaire is relatively inexpensive. Even if you mail your survey and have to pay for postage, it’s far less expensive and time consuming than it would be to interview dozens or hundreds of respondents in person. However, it can take significant time to identify who you want to survey.
While surveys are advantageous in many respects, they’re not perfect! One of the biggest drawbacks with surveys is their inflexibility, which is to say, your questionnaire is your only means of collecting data. All you have is their answers to the questions, and if they don’t understand or interpret on of your questions correctly you might not get good data back. In addition, people aren’t great at accurately answering survey questions, even when they try. We’ll talk about ways to address that concern later though.
There are a variety of ways in which a survey can be administered. Remember, how you conduct your survey—as well as when you administer it—will impact your response rate . Ideally, 100% of the people you send your survey to would send it back, but that will never happen. People are busy, they lose them, or they might just not care. Even offering a reward (money, gift cards, etc.) wont guarantee people will take the time to respond. Thus, it’s important to structure your survey in a way that helps to secure as many responses as possible. The response rate just refers to the percentage of people that the survey was sent to that you recieve a response from.
A traditional way to administer surveys is in the form of a self-administered questionnaire, a paper-and-pencil survey, in which participants are given a set of questions they respond to and then return either by mail or in person. Alternatively, it is increasingly common and cost effective to administer surveys online. Alternatively, you can also see people in person (door to door or standing in public spaces) and ask them to fill out the questionnaire.
The 2020 U.S. Census, for example, includes options to respond by mail, phone or online in an effort to produce a high response rate and more complete data.
An additional considerations is how you want to administer your survey with respect to time, and whether you want to survey your population at a single point or over an extended period.
One option is a cross-sectional survey , which is given at just one point in time. Such a survey will tell you how things were for the respondents at the particular time, such as who they would support in the presidential election in the third week of August. The respondents answers might change before and after the survey, so you’re essentially getting a snapshot of views and feelings at that moment.
A longitudinal survey , on the other hand, lets you make observations over an extended period of time. There are several types of longitudinal surveys you can conduct. Three of the mains ones are: trend, panel, and cohort surveys.
Trend surveys, as the name suggests, measure trends. If you conduct a trend survey, you are studying how people’s thoughts and views change over time. For example, if you want to know how Americans’ views on healthcare have changed over the past 10 years, you would ask the same questions to people at different points in time over a 10-year period. You wouldn’t have to survey the same people each time because as a researcher you’re more interested in the generalized trend over time than who is being sampled each time. What is critical is asking the same question worded the same way, to capture changes in people’s views.
A panel survey, on the other hand, focuses on the same people each time the survey is administered. An example of this would be if you studied the effects of exercise on 100 kids over a 10-year period beginning at age 12 and following them until they are 22. These surveys can produce impressive results. On the downside, however, panel surveys are costly and difficult to manage. It’s hard to keep track of dozens of people over a period of many years as they relocate, change jobs or names and pass away. As such, panel surveys take considerable resources and investment to administer.
A third type of longitudinal survey is a cohort survey, in which you identify a category of people of interest then randomly select individuals from within that category to survey over time. It is important to note that you don’t have to pick the same people each year; however, the people you do pick must fall into the same categories that you have previously selected. For instance in 1951 the British Doctors Study began by studying people who were exposed to smoking to understand whether it had an impact on the likelihood of lung cancer. They matched people who did smoke to non-smokers, and planned to continue tracking those two groups until 2001. However, it only took until 1956 for them to find convincing evidence that smoking increased cancer rates.
Which type of survey is best for you? It depends on the nature of your research project and the questions you’re trying to answer. Generally speaking, longitudinal surveys give us more information about trends, tendencies, opinions or ideas over a long period of time. Cross-sectional surveys have limited explanatory power because they only capture one moment. For instance, if I do a survey and find that healthier people are more likely to report riding their bike, do they bike because they’re healthy or are they healthy because they bike? We can’t tell just from that survey. However, if we survey the same people multiple times and see how biking and health change over time we can better identify the causal effect.
So why don’t we make every survey longitudinal? Because they can be costly and difficult to administer, and your research work may not require a temporal data analysis. Getting a high response rate on one survey is difficult, getting people to respond multiple times just compounds the problem. What’s important is that you understand the pros and cons of each type of survey and use the method that will produce, for you, the most meaningful data.
With survey’s it isn’t enough to just ask a question. You have to ask the right question. To get good information you have to be aware of all the ways your question could be misunderstood or could produce unreliable information. And first and foremost, you have to be aware that the thing you’re studying (humans) are complicated. We lie. We answer incorrectly. We randomly guess and answer questions we don’t have an answer for. We’re not very good at assessing ourselves. That’s why everyone makes the joke about 75% of drivers believing they’re above average drivers.
Let’s work through some of the things that can go wrong in your survey questions.
It is critical to avoid creating questions that could prompt respondents to give a socially desirable answer instead of an accurate one. In research, social desirability refers to the idea that respondents will try to answer questions in a way that will present them in a favorable light. Imagine asking a survey question regarding sensitive topics like abortion or racism to respondents. Some people might answer those types of questions without stating their true belief in order to appear socially acceptable, and so in general we know people will under report these behaviors. That makes them more difficult to study through a survey, but not impossible.
To take one example, what do you do if you want to run a survey on binge drinking at colleges? Simply asking a direct question like below probably wont produce accurate results.
One approach would be to ask the question multiple ways, giving people more opportunities to answer. And you’ll likely want to be specific in your questions. People might not consider themselves to be binge drinkers (or unfaithful, or racist, etc.), but if you ask whether they’ve had more than 5 drinks in one sitting the past week, they may be more honest about that without realizing that might make them a binge drinker. And asking factual-behavior based questions may help to avoid incorrect self appraisals.
Another problematic survey question is one that contains multiple questions, yet is posed as one single question. This is called a double-barreled question and has the potential to confuse the respondent. Take the question below for example about recent movies. If someone answers ‘Yes’ is it because they think new movies are too long or unoriginal, or both? We don’t know, it might be both, it might just be one. If you find the word “and” or “or” in your question, seriously think about breaking it into two separate questions.
As we’ve discussed, people will lie and may do a poor job of accurately reporting information on themselves. In addition, there is no one single understanding of many terms, such as toughness, happiness, risk-aversion, etc. As such, you can’t just ask a respondent if they’re “tough” and expect to get an accurate response. A better strategy might be to ask multiple overlapping questions related to toughness, which together will help to approximate their personality.
You might expect people that are kind or optimistic will respond the same to every question, but that rarely happens. Changing the direction of a question from a positive wording to a negative wording can really shift how people evaluate themselves. For instance, asking whether someone is considerate, and someone is not considerate can produce opposite reactions. People typically aren’t kind or unkind, they exist on a spectrum between those two extremes. Asking multiple questions helps to identify where they exist within that continuum. For instance, see the questions below on toughness, which are pulled from the International Personality Item Pool , a database of survey questions that can be used to measure different personality traits. Taking these questions together and using them to measure whether someone is very tough, or sorta tough, or not tough, will give a more accurate result.
If you choose to only ask some questions about issues that only a few of your respondents have had experience with or may find relevant, it’s a good idea to use a filter question in your survey. A filter question is designed to identify some subset of survey respondents who are asked additional questions that are not relevant to the entire sample. Online surveys make filter questions a lot easier, because you can manually control what questions respondents see based on their answers. In the example below, we have to trust that the respondent understands whether to skip the next question or not.
You also may want to make sure that your respondents are reading the questions. Let’s be honest, we’ve all filled out a survey and just started randomly checking boxes to get it done faster. You can add an attention filter by telling the respondent which option to choose, to make sure they’re taking the time to answer accurately. Once you see who gets the attention filter question wrong, you can remove their answers from the final data, since you won’t know whether they answered any of the other questions correctly.
So, you’ve created clear, concise, and understandable survey questions, but have you put much thought into your response options? Response options are the answers that you provide to the people taking your survey. Researchers can choose from a number of response options, but like everything else in surveys there’s no one right option for all questions. The best option for any question will be determined by the purposes of the research and the question being asked.
One crucial consideration is whether your questions will be close-ended or open-ended. A close-ended question means the respondent must choose between a limited number of pre-determined responses to the question. Close-ended questions are often used in quantitative research because the responses can be counted up more readily (55% of respondents said Yes to supporting free puppies for all, etc.).
When designing responses to close-ended questions, it’s important to ensure that the responses offered are both exhaustive and mutually exclusive . Making responses exhaustive means that every possible answer that a respondent could have can fit into one of the responses. When responses are mutually exclusive, on the other hand, there are no possible answers a respondent could have that might fit into more than one category simultaneously. Imagine a survey in which respondents are asked how many children they have. They can select from the following responses: “Zero”; “One”; “Two”; “Three”; and “Four or More”. The responses are exhaustive because whether the respondent has no children or fifty children, there is an accurate response for them to choose. The responses are mutually exclusive as well because no matter how many children they have, there is only one accurate response. Making response options both exhaustive and mutually exclusive helps ensure that every respondent can answer questions effectively and helps improve the accuracy of the data collected by reducing errors. If the responses can’t be mutually exclusive you can also allow respondents to choose multiple options.
Survey questions can also be open-ended , meaning the respondent has the opportunity to answer the question in their own words, without pre-determined response options. Open-ended questions have the advantage of allowing the respondent to share more detailed information, and to share opinions or information that the researcher might not have thought to ask about. On the other hand, analysis of open-ended questions can be more difficult because the responses are harder to measure. Open ended questions also take a lot more time from your respondents and can lead to fatigue, so they should generally be used sparingly.
Giving people only the options to select yes or no can make it difficult for respondents to answer honestly. Do you like to break the rules? You might think sometimes, if you really need to, but you don’t break the rules all the time. So would you say yes or no? Giving people a range of responses will allow them to give a more accurate response.
One common response option for close-ended survey questions is known as the Likert scale. A Likert scale allows a respondent to evaluate a statement using a range of possible options. This range is balanced, with an equal number of positive and negative choices, and often includes a neutral option. Likert scales most commonly measure agreement and disagreement, and often have five or seven response options, though they could conceivably include any number of choices. See the examples below.
Alternatively, respondents can be give the option to rate their agreement or reaction to a question using numeric options such as 0-5, 0-10, 0-100, etc.. Respondents may feel that they fall somewhere in between strongly agreeing and somewhat agreeing, so numeric responses allow them more freedom, however you wont know what a person thinks a 7 versus an 8 is in that case.
When using a Likert Scale, or a similar response option, researchers should be careful and intentional about whether to choose a neutral option, such as the “Neither Agree nor Disagree” option mentioned above. Doing so can encourage respondents to engage in related behaviors such as fence-sitting and floating. Fence-sitting refers to a respondent choosing a neutral option, even when they have an opinion. Floating refers to the opposite, when a respondent chooses an opinion that they don’t hold because there isn’t a neutral option. Both have the potential to influence a survey’s data, so researchers should be careful to anticipate whether one or the other might be a problem, and whether a neutral option is appropriate for a particular question.
After reading this chapter you might realize there is a lot more nuance to designing surveys than you previously thought. With all these options and variables, how can the average researcher know they’ve designed the best survey for their particular research? One crucial step they can take is to conduct pre-testing. Pre-testing , as the name suggests, refers to sending out the survey to a sample of people before the actual research is conducted. Doing so can help the researcher understand how the respondents interact with the survey, including how long it takes, what questions are confusing or unclear, and if any of your questions are controversial. In this way, pre-testing is a necessary and invaluable way for researchers to identify problems with their surveys before the research is conducted.
So you’ve run your survey. What does the data tell you, aren’t the answers jumping out at you? A survey is just the data collection – it won’t tell you anything anything on its own. The first thing you’ll need to do is code your survey so that it’s ready for analysis. The survey that was shown at the beginning of the chapter was done on pen and paper, so it had to be manually entered into a spreadsheet for analysis. As we discussed, quantitative research generally means using numbers and statistical techniques, so all those question you asked have to be converted. Look at the “code sheet” used to code that survey below.
Once the answers get coded into a spreadsheet, your data is ready for analysis. We’ll talk about the steps of that analysis in future chapters though, don’t worry. For now, you’re done with the survey, and we’ll move to another prominent method – interviews.
Learn all about quantitative research surveys, including types of quantitative survey questions, question formats, and quantitative question examples.
Jan 29, 2024
quantilope is the Consumer Intelligence Platform for all end-to-end research needs
In a quantitative research study brands will gather numeric data for most of their questions through formats like numerical scale questions or ranking questions. However, brands can also include some non-quantitative questions throughout their quantitative study - like open-ended questions, where respondents will type in their own feedback to a question prompt. Even so, open-ended answers can be numerically coded to sift through feedback easily (e.g. anyone who writes in 'Pepsi' in a soda study would be assigned the number '1', to look at Pepsi feedback as a whole). One of the biggest benefits of using a quantitative research approach is that insights around a research topic can undergo statistical analysis; the same can’t be said for qualitative data like focus group feedback or interviews. Another major difference between quantitative and qualitative research methods is that quantitative surveys require respondents to choose from a limited number of choices in a close-ended question - generating clear, actionable takeaways. However, these distinct quantitative takeaways often pair well with freeform qualitative responses - making quant and qual a great team to use together. The rest of this article focuses on quantitative research, taking a closer look at quantitative survey question types and question formats/layouts.
Back to table of contents
Quantitative questions come in many forms, each with different benefits depending on dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139784">your dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139740">market research objectives. Below we’ll explore some of these dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139745">quantitative dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139785">survey question dropdown#toggle" data-dropdown-menu-id-param="menu_term_281139785" data-dropdown-placement-param="top" data-term-id="281139785"> types, which are commonly used together in a single survey to keep things interesting for dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents . The style of questioning used during dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139739">quantitative dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139750">data dropdown#toggle" data-dropdown-menu-id-param="menu_term_281139750" data-dropdown-placement-param="top" data-term-id="281139750"> collection is important, as a good mix of the right types of questions will deliver rich data, limit dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondent fatigue, and optimize the dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139757">response rate . dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139742">Questionnaires should be enjoyable - and varying the dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139755">types of dropdown#toggle" data-dropdown-menu-id-param="menu_term_281139755" data-dropdown-placement-param="top" data-term-id="281139755">quantitative research dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139755"> questions used throughout your survey will help achieve that.
dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139763">Descriptive research questions (also known as usage and attitude, or, U&A questions) seek a general indication or prediction about how a dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139773">group of people behaves or will behave, how that group is characterized, or how a group thinks.
For example, a business might want to know what portion of adult men shave, and how often they do so. To find this out, they will survey men (the dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139743">target audience ) and ask descriptive questions about their frequency of shaving (e.g. daily, a few times a week, once per week, and so on.) Each of these frequencies get assigned a numerical ‘code’ so that it’s simple to chart and analyze the data later on; daily might be assigned ‘5’, a few times a week might be assigned ‘4’, and so on. That way, brands can create charts using the ‘top two’ and ‘bottom two’ values in a descriptive question to view these metrics side by side.
Another business might want to know how important local transit issues are to residents, so dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139745">quantitative survey questions will allow dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents to indicate the degrees of opinion attached to various transit issues. Perhaps the transit business running this survey would use a sliding numeric scale to see how important a particular issue is.
dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139782">Comparative research questions are concerned with comparing individuals or groups of people based on one or more variables. These questions might be posed when a business wants to find out which segment of its dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139743">target audience might be more profitable, or which types of products might appeal to different sets of consumers.
For example, a business might want to know how the popularity of its chocolate bars is spread out across its entire customer base (i.e. do women prefer a certain flavor? Are children drawn to candy bars by certain packaging attributes? etc.). Questions in this case will be designed to profile and ‘compare’ segments of the market.
Other businesses might be looking to compare coffee consumption among older and younger consumers (i.e. dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139741">demographic segments), the difference in smartphone usage between younger men and women, or how women from different regions differ in their approach to skincare.
As the name suggests, relationship-based survey questions are concerned with the relationship between two or more variables within one or more dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139741">demographic groups. This might be a dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139759">causal link between one thing and the other - for example, the consumption of caffeine and dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents ’ reported energy levels throughout the day. In this case, a coffee or energy drink brand might be interested in how energy levels differ between those who drink their caffeinated line of beverages and those who drink decaf/non-caffeinated beverages.
Alternatively, it might be a case of two or more factors co-existing, without there necessarily being a dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139759">causal link - for example, a particular type of air freshener being more popular amongst a certain dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139741">demographic (maybe one that is controlled wirelessly via Bluetooth is more popular among younger homeowners than one that’s plugged into the wall with no controls). Knowing that millennials favor air fresheners which have options for swapping out scents and setting up schedules would be valuable information for new product development.
Aside from descriptive, comparative, and relationship-based survey questions, brands can opt to include advanced methodologies in their quantitative dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139742">questionnaire for richer depth. Though advanced methods are more complex in terms of the insights output, quantilope’s Consumer Intelligence Platform automates the setup and analysis of these methods so that researchers of any background or skillset can leverage them with ease.
With quantilope’s pre-programmed suite of 12 advanced methodologies , including MaxDiff , TURF , Implicit , and more, users can drag and drop any of these into a dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139742">questionnaire and customize for their own dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139740">market research objectives.
For example, consider a beverage company that’s looking to expand its flavor profiles. This brand would benefit from a MaxDiff which forces dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents to make tradeoff decisions between a set of flavors. A dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondent might say that coconut is their most-preferred flavor, and lime their least (when in a consideration set with strawberry), yet later on in the MaxDiff that same dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondent may say Strawberry is their most-preferred flavor (over black cherry and kiwi). While this is just one example of an advanced method, instantly you can see how much richer and more actionable these quantitative metrics become compared to a standard usage and attitude question .
Advanced methods can be used alongside descriptive, comparison, or relationship questions to add a new layer of context wherever a business sees fit. Back to table of contents
So we’ve covered the kinds of dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139736">quantitative research questions you might want to answer using dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139740">market research , but how do these translate into the actual format of questions that you might include on your dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139742">questionnaire ?
Thinking ahead to your reporting process during your dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139742">questionnaire setup is actually quite important, as the available chart types differ among the types of questions asked; some question data is compatible with bar chart displays, others pie charts, others in trended line graphs, etc. Also consider how well the questions you’re asking will translate onto different devices that your dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents might be using to complete the survey (mobile, PC, or tablet).
Single select questions are the simplest form of quantitative questioning, as dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents are asked to choose just one answer from a list of items, which tend to be ‘either/or’, ‘yes/no’, or ‘true/false’ questions. These questions are useful when you need to get a clear answer without any qualifying nuances.
Multi-select questions (aka, dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139767">multiple choice ) offer more flexibility for responses, allowing for a number of responses on a single question. dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">Respondents can be asked to ‘check all that apply’ or a cap can be applied (e.g. ‘select up to 3 choices’).
For example:
Aside from asking text-based questions like the above examples, a brand could also use a single or multi-select question to ask respondents to select the image they prefer more (like different iterations of a logo design, packaging options, branding colors, etc.).
A dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139749">Likert scale is widely used as a convenient and easy-to-interpret rating method. dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">Respondents find it easy to indicate their degree of feelings by selecting the response they most identify with.
Slider scales are another good interactive way of formatting questions. They allow dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents to customize their level of feeling about a question, with a bit more variance and nuance allowed than a numeric scale:
One particularly common use of a slider scale in a dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139740">market dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139770">research dropdown#toggle" data-dropdown-menu-id-param="menu_term_281139770" data-dropdown-placement-param="top" data-term-id="281139770"> study is known as a NPS (Net Promoter Score) - a way to measure dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139775">customer experience and loyalty . A 0-10 scale is used to ask customers how likely they are to recommend a brand’s product or services to others. The NPS score is calculated by subtracting the percentage of ‘detractors’ (those who respond with a 0-6) from the percentage of promoters (those who respond with a 9-10). dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">Respondents who select 7-8 are known as ‘passives’.
For example:
Drag-and-drop question formats are a more ‘gamified’ approach to survey capture as they ask dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents to do more than simply check boxes or slide a scale. Drag-and-drop question formats are great for ranking exercises - asking dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents to place answer options in a certain order by dragging with their mouse. For example, you could ask survey takers to put pizza toppings in order of preference by dragging options from a list of possible answers to a box displaying their personal preferences:
Matrix questions are a great way to consolidate a number of questions that ask for the same type of response (e.g. single select yes/no, true/false, or multi-select lists). They are mutually beneficial - making a survey look less daunting for the dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondent , and easier for a brand to set up than asking multiple separate questions.
Items in a matrix question are presented one by one, as respondents cycle through the pages selecting one answer for each coffee flavor shown.
While the above example shows a single-matrix question - meaning a respondent can only select one answer per element (in this case, coffee flavors), a matrix setup can also be used for multiple-choice questions - allowing respondents to choose multiple answers per element shown, or for rating questions - allowing respondents to assign a rating (e.g. 1-5) for a list of elements at once. Back to table of contents
We’ve reviewed the types of questions you might ask in a quantitative survey, and how you might format those questions, but now for the actual crafting of the content.
When considering which questions to include in your survey, you’ll first want to establish what your research goals are and how these relate to your business goals. For example, thinking about the three types of dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139745">quantitative survey questions explained above - descriptive, comparative, and relationship-based - which type (or which combination) will best meet your research needs? The questions you ask dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents may be phrased in similar ways no matter what kind of layout you leverage, but you should have a good idea of how you’ll want to analyze the results as that will make it much easier to correctly set up your survey.
Quantitative questions tend to start with words like ‘how much,’ ‘how often,’ ‘to what degree,’ ‘what do you think of,’ ‘which of the following’ - anything that establishes what consumers do or think and that can be assigned a numerical code or value. Be sure to also include ‘other’ or ‘none of the above’ options in your quant questions, accommodating those who don’t feel the pre-set answers reflect their true opinion. As mentioned earlier, you can always include a small number of dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139748">open-ended questions in your quant survey to account for any ideas or expanded feedback that the pre-coded questions don’t (or can’t) cover. Back to table of contents
dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139745">Quantitative survey questions impose limits on the answers that dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents can choose from, and this is a good thing when it comes to measuring consumer opinions on a large scale and comparing across dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents . A large volume of freeform, open-ended answers is interesting when looking for themes from qualitative studies, but impractical to wade through when dealing with a large dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139756">sample size , and impossible to subject to dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139774">statistical analysis .
For example, a quantitative survey might aim to establish consumers' smartphone habits. This could include their frequency of buying a new smartphone, the considerations that drive purchase, which features they use their phone for, and how much they like their smartphone.
Some examples of quantitative survey questions relating to these habits would be:
Q. How often do you buy a new smartphone?
[single select question]
More than once per year
Every 1-2 years
Every 3-5 years
Every 6+ years
Q. Thinking about when you buy a smartphone, please rank the following factors in order of importance:
[drag and drop ranking question]
screen size
storage capacity
Q. How often do you use the following features on your smartphone?
[matrix question]
|
|
|
| ||
Q. How do you feel about your current smartphone?
[sliding scale]
I love it <-------> I hate it
Answers from these above questions, and others within the survey, would be analyzed to paint a picture of smartphone usage and attitude trends across a population and its sub-groups. dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139738">Qualitative research might then be carried out to explore those findings further - for example, people’s detailed attitudes towards their smartphones, how they feel about the amount of time they spend on it, and how features could be improved. Back to table of contents
quantilope’s Consumer Intelligence Platform specializes in automated, advanced survey insights so that researchers of any skill level can benefit from quick, high-quality consumer insights. With 12 advanced methods to choose from and a wide variety of quantitative question formats, quantilope is your one-stop-shop for all things dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139740">market research (including its dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139776">in-depth dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139738">qualitative research solution - inColor ).
When it comes to building your survey, you decide how you want to go about it. You can start with a blank slate and drop questions into your survey from a pre-programmed list, or you can get a head start with a survey dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139765">template for a particular business use case (like concept testing ) and customize from there. Once your survey is ready to launch, simply specify your dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139743">target audience , connect any panel (quantilope is panel agnostic), and watch as dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139737">respondents dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139783">answer questions in your survey in real-time by monitoring the fieldwork section of your project. AI-driven dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139764">data analysis takes the raw data and converts it into actionable findings so you never have to worry about manual calculations or statistical testing.
Whether you want to run your quantitative study entirely on your own or with the help of a classically trained research team member, the choice is yours on quantilope’s platform. For more information on how quantilope can help with your next dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139736">quantitative dropdown#toggle" data-dropdown-placement-param="top" data-term-id="281139768">research dropdown#toggle" data-dropdown-menu-id-param="menu_term_281139768" data-dropdown-placement-param="top" data-term-id="281139768"> project , get in touch below!
Latest articles.
Discover how A&W's application of advanced research methods has enabled its insights team to deliver data-driven recommendations with actio...
September 09, 2024
In this guide, we'll break down the essentials of idea screening, starting by defining its purpose and exploring the top techniques for suc...
September 04, 2024
Introducing quantilope's new brand experience featuring a brighter, fresher look and feel.
Run a free plagiarism check in 10 minutes, generate accurate citations for free.
Methodology
Published on April 12, 2019 by Raimo Streefkerk . Revised on June 22, 2023.
When collecting and analyzing data, quantitative research deals with numbers and statistics, while qualitative research deals with words and meanings. Both are important for gaining different kinds of knowledge.
Common quantitative methods include experiments, observations recorded as numbers, and surveys with closed-ended questions.
Quantitative research is at risk for research biases including information bias , omitted variable bias , sampling bias , or selection bias . Qualitative research Qualitative research is expressed in words . It is used to understand concepts, thoughts or experiences. This type of research enables you to gather in-depth insights on topics that are not well understood.
Common qualitative methods include interviews with open-ended questions, observations described in words, and literature reviews that explore concepts and theories.
The differences between quantitative and qualitative research, data collection methods, when to use qualitative vs. quantitative research, how to analyze qualitative and quantitative data, other interesting articles, frequently asked questions about qualitative and quantitative research.
Quantitative and qualitative research use different research methods to collect and analyze data, and they allow you to answer different kinds of research questions.
Quantitative and qualitative data can be collected using various methods. It is important to use a data collection method that will help answer your research question(s).
Many data collection methods can be either qualitative or quantitative. For example, in surveys, observational studies or case studies , your data can be represented as numbers (e.g., using rating scales or counting frequencies) or as words (e.g., with open-ended questions or descriptions of what you observe).
However, some methods are more commonly used in one type or the other.
A rule of thumb for deciding whether to use qualitative or quantitative data is:
For most research topics you can choose a qualitative, quantitative or mixed methods approach . Which type you choose depends on, among other things, whether you’re taking an inductive vs. deductive research approach ; your research question(s) ; whether you’re doing experimental , correlational , or descriptive research ; and practical considerations such as time, money, availability of data, and access to respondents.
You survey 300 students at your university and ask them questions such as: “on a scale from 1-5, how satisfied are your with your professors?”
You can perform statistical analysis on the data and draw conclusions such as: “on average students rated their professors 4.4”.
You conduct in-depth interviews with 15 students and ask them open-ended questions such as: “How satisfied are you with your studies?”, “What is the most positive aspect of your study program?” and “What can be done to improve the study program?”
Based on the answers you get you can ask follow-up questions to clarify things. You transcribe all interviews using transcription software and try to find commonalities and patterns.
You conduct interviews to find out how satisfied students are with their studies. Through open-ended questions you learn things you never thought about before and gain new insights. Later, you use a survey to test these insights on a larger scale.
It’s also possible to start with a survey to find out the overall trends, followed by interviews to better understand the reasons behind the trends.
Qualitative or quantitative data by itself can’t prove or demonstrate anything, but has to be analyzed to show its meaning in relation to the research questions. The method of analysis differs for each type of data.
Quantitative data is based on numbers. Simple math or more advanced statistical analysis is used to discover commonalities or patterns in the data. The results are often reported in graphs and tables.
Applications such as Excel, SPSS, or R can be used to calculate things like:
Qualitative data is more difficult to analyze than quantitative data. It consists of text, images or videos instead of numbers.
Some common approaches to analyzing qualitative data include:
If you want to know more about statistics , methodology , or research bias , make sure to check out some of our other articles with explanations and examples.
Research bias
Quantitative research deals with numbers and statistics, while qualitative research deals with words and meanings.
Quantitative methods allow you to systematically measure variables and test hypotheses . Qualitative methods allow you to explore concepts and experiences in more detail.
In mixed methods research , you use both qualitative and quantitative data collection and analysis methods to answer your research question .
The research methods you use depend on the type of data you need to answer your research question .
Data collection is the systematic process by which observations or measurements are gathered in research. It is used in many different contexts by academics, governments, businesses, and other organizations.
There are various approaches to qualitative data analysis , but they all share five steps in common:
The specifics of each step depend on the focus of the analysis. Some common approaches include textual analysis , thematic analysis , and discourse analysis .
A research project is an academic, scientific, or professional undertaking to answer a research question . Research projects can take many forms, such as qualitative or quantitative , descriptive , longitudinal , experimental , or correlational . What kind of research approach you choose will depend on your topic.
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 Citation Generator.
Streefkerk, R. (2023, June 22). Qualitative vs. Quantitative Research | Differences, Examples & Methods. Scribbr. Retrieved September 13, 2024, from https://www.scribbr.com/methodology/qualitative-quantitative-research/
Other students also liked, what is quantitative research | definition, uses & methods, what is qualitative research | methods & examples, mixed methods research | definition, guide & examples, get unlimited documents corrected.
✔ Free APA citation check included ✔ Unlimited document corrections ✔ Specialized in correcting academic texts
IMAGES
VIDEO
COMMENTS
Survey research is defined as "the collection of information from a sample of individuals through their responses to questions" (Check & Schutt, 2012, p. 160). This type of research allows for a variety of methods to recruit participants, collect data, and utilize various methods of instrumentation. Survey research can use quantitative research ...
Survey research uses a list of questions to collect data about a group of people. You can conduct surveys online, by mail, or in person. ... Sending out a paper survey by mail is a common method of gathering demographic information (for example, in a government census of the population). ... Quantitative research is expressed in numbers and is ...
INTRODUCTION. Scientific research is usually initiated by posing evidenced-based research questions which are then explicitly restated as hypotheses.1,2 The hypotheses provide directions to guide the study, solutions, explanations, and expected results.3,4 Both research questions and hypotheses are essentially formulated based on conventional theories and real-world processes, which allow the ...
Survey Research. Definition: Survey Research is a quantitative research method that involves collecting standardized data from a sample of individuals or groups through the use of structured questionnaires or interviews. The data collected is then analyzed statistically to identify patterns and relationships between variables, and to draw conclusions about the population being studied.
Abstract. In an era of data-driven decision-making, a comprehensive understanding of quantitative research is indispensable. Current guides often provide fragmented insights, failing to offer a holistic view, while more comprehensive sources remain lengthy and less accessible, hindered by physical and proprietary barriers.
Quantitative methods emphasize objective measurements and the statistical, mathematical, or numerical analysis of data collected through polls, questionnaires, and surveys, or by manipulating pre-existing statistical data using computational techniques.Quantitative research focuses on gathering numerical data and generalizing it across groups of people or to explain a particular phenomenon.
Survey research means collecting information about a group of people by asking them questions and analysing the results. To conduct an effective survey, follow these six steps: Determine who will participate in the survey. Decide the type of survey (mail, online, or in-person) Design the survey questions and layout. Distribute the survey.
The traditional definition of survey research is a quantitative method for collecting information from a pool of respondents by asking multiple survey questions. This research type includes the recruitment of individuals collection, and analysis of data. ... online surveys are extremely economical compared to paper-based surveys. Versatile ...
Revised on June 22, 2023. Quantitative research is the process of collecting and analyzing numerical data. It can be used to find patterns and averages, make predictions, test causal relationships, and generalize results to wider populations. Quantitative research is the opposite of qualitative research, which involves collecting and analyzing ...
Historically, surveys have been seen as an exclusively quantitative research method but this is really an outmoded view. A carefully designed survey can generate significant amounts of qualitative data that can enhance and illuminate the quantitative product of surveys (e.g. McBeath 2019; McBeath et al. 2019).
This research paper offers a thorough examination of the benefits and drawbacks of applying quantitative methods to research in a range of academic fields.
This paper focuses on the research approach adopted to measure organizational efficiency based on international best practices and conducts a comparative analysis on the local organizations from a ...
Summarizing quantitative data and its effective presentation and discussion can be challenging for students and researchers. This chapter provides a framework for adequately reporting findings from quantitative analysis in a research study for those contemplating to write a research paper. The rationale underpinning the reporting methods to ...
Quantitative research explains phenomena by collecting numerical unchanging d etailed data t hat. are analyzed using mathematically based methods, in particular statistics that pose questions of ...
Within the medical realm, there are three main types of survey: epidemiological surveys, surveys on attitudes to a health service or intervention and questionnaires assessing knowledge on a particular issue or topic. 1. Despite a widespread perception that surveys are easy to conduct, in order to yield meaningful results, a survey needs ...
The questionnaire, or survey can be written documentation that is administered either in person (door-to-door), on paper (through the mail), by phone, or online. Survey research is a quantitative method that uses predetermined questions that aim to describe or explain features of a very large group or groups. Surveys are really common.
Abstract. Survey methodologies, usually using questionnaires, are among the most popular in. the social sciences, but they are also among the most mis-used. The ir popularity in. small-scale ...
The rest of this article focuses on quantitative research, taking a closer look at quantitative survey question types and question formats/layouts. Back to table of contents . Types of quantitative survey questions - with examples . Quantitative questions come in many forms, each with different benefits depending on your market research objectives.
Questionnaires vs. surveys. A survey is a research method where you collect and analyze data from a group of people. A questionnaire is a specific tool or instrument for collecting the data.. Designing a questionnaire means creating valid and reliable questions that address your research objectives, placing them in a useful order, and selecting an appropriate method for administration.
This paper revisits this debate and updates ... it with new contributions on the use and misuse of the 'household' in surveys and censuses, particularly in quantitative research designs ...
A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic. There are five key steps to writing a literature review:
For this research, a general quantitative survey method will be used due to its speed, efficiency and cost-effectiveness (Gürbüz, 2017). The survey is based on the CoI survey by Arnaugh et al ...
Quantitative research Quantitative research is expressed in numbers and graphs. It is used to test or confirm theories and assumptions. This type of research can be used to establish generalizable facts. about a topic. Common quantitative methods include experiments, observations recorded as numbers, and surveys with closed-ended questions.