statistics in research paper

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals

Statistics articles from across Nature Portfolio

Statistics is the application of mathematical concepts to understanding and analysing large collections of data. A central tenet of statistics is to describe the variations in a data set or population using probability distributions. This analysis aids understanding of what underlies these variations and enables predictions of future changes.

Latest Research and Reviews

Analysis of player speed and angle toward the ball in soccer

• Álvaro Novillo
• Antonio Cordón-Carmona
• Javier M. Buldú

Medical history predicts phenome-wide disease onset and enables the rapid response to emerging health threats

Preventive interventions often require strategies to identify high-risk individuals. Here, the authors illustrate the potential utility of medical history in predicting the onset risk for thousands of diseases across clinical specialties including COVID-19.

• Jakob Steinfeldt
• Benjamin Wild
• Roland Eils

Unsupervised detection of large-scale weather patterns in the northern hemisphere via Markov State Modelling: from blockings to teleconnections

• Sebastian Springer
• Alessandro Laio
• Valerio Lucarini

Modified correlated measurement errors model for estimation of population mean utilizing auxiliary information

• Housila P. Singh

Employing machine learning for enhanced abdominal fat prediction in cavitation post-treatment

• Doaa A. Abdel Hady
• Omar M. Mabrouk
• Tarek Abd El-Hafeez

Unexpected HCHO transnational transport: influence on the temporal and spatial distribution of HCHO in Tibet from 2013 to 2021 based on satellite

News and Comment

Efficient learning of many-body systems

The Hamiltonian describing a quantum many-body system can be learned using measurements in thermal equilibrium. Now, a learning algorithm applicable to many natural systems has been found that requires exponentially fewer measurements than existing methods.

Fudging the volcano-plot without dredging the data

Selecting omic biomarkers using both their effect size and their differential status significance ( i.e. , selecting the “volcano-plot outer spray”) has long been equally biologically relevant and statistically troublesome. However, recent proposals are paving the way to resolving this dilemma.

• Thomas Burger

Disentangling truth from bias in naturally occurring data

A technique that leverages duplicate records in crowdsourcing data could help to mitigate the effects of biases in research and services that are dependent on government records.

• Daniel T. O’Brien

Sciama’s argument on life in a random universe and distinguishing apples from oranges

Dennis Sciama has argued that the existence of life depends on many quantities—the fundamental constants—so in a random universe life should be highly unlikely. However, without full knowledge of these constants, his argument implies a universe that could appear to be ‘intelligently designed’.

• Zhi-Wei Wang
• Samuel L. Braunstein

A method for generating constrained surrogate power laws

A paper in Physical Review X presents a method for numerically generating data sequences that are as likely to be observed under a power law as a given observed dataset.

• Zoe Budrikis

Connected climate tipping elements

Tipping elements are regions that are vulnerable to climate change and capable of sudden drastic changes. Now research establishes long-distance linkages between tipping elements, with the network analysis offering insights into their interactions on a global scale.

• Valerie N. Livina

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Statistical Papers

Statistical Papers is a forum for presentation and critical assessment of statistical methods encouraging the discussion of methodological foundations and potential applications.

• The Journal stresses statistical methods that have broad applications, giving special attention to those relevant to the economic and social sciences.
• Covers all topics of modern data science, such as frequentist and Bayesian design and inference as well as statistical learning.
• Contains original research papers (regular articles), survey articles, short communications, reports on statistical software, and book reviews.
• High author satisfaction with 90% likely to publish in the journal again.
• Werner G. Müller,
• Carsten Jentsch,
• Shuangzhe Liu,
• Ulrike Schneider

Latest issue

Volume 65, Issue 2

Latest articles

Covariance structure tests for multivariate t -distribution.

• Katarzyna Filipiak

A non-classical parameterization for density estimation using sample moments

• Anders Lindquist

Geometric infinitely divisible autoregressive models

• Monika S. Dhull

A mixture distribution for modelling bivariate ordinal data

• Ryan H. L. Ip
• K. Y. K. Wu

Analyzing quantitative performance: Bayesian estimation of 3-component mixture geometric distributions based on Kumaraswamy prior

• Nadeem Akhtar
• Sajjad Ahmad Khan
• Haifa Alqahtani

Journal updates

Write & submit: overleaf latex template.

Overleaf LaTeX Template

Journal information

• Australian Business Deans Council (ABDC) Journal Quality List
• Current Index to Statistics
• Google Scholar
• Japanese Science and Technology Agency (JST)
• Mathematical Reviews
• Norwegian Register for Scientific Journals and Series
• OCLC WorldCat Discovery Service
• Research Papers in Economics (RePEc)
• Science Citation Index Expanded (SCIE)
• TD Net Discovery Service
• UGC-CARE List (India)

Rights and permissions

Editorial policies

© Springer-Verlag GmbH Germany, part of Springer Nature

• Find a journal
• Publish with us
• Track your research

Effective Use of Statistics in Research – Methods and Tools for Data Analysis

Remember that impending feeling you get when you are asked to analyze your data! Now that you have all the required raw data, you need to statistically prove your hypothesis. Representing your numerical data as part of statistics in research will also help in breaking the stereotype of being a biology student who can’t do math.

Statistical methods are essential for scientific research. In fact, statistical methods dominate the scientific research as they include planning, designing, collecting data, analyzing, drawing meaningful interpretation and reporting of research findings. Furthermore, the results acquired from research project are meaningless raw data unless analyzed with statistical tools. Therefore, determining statistics in research is of utmost necessity to justify research findings. In this article, we will discuss how using statistical methods for biology could help draw meaningful conclusion to analyze biological studies.

Table of Contents

Role of Statistics in Biological Research

Statistics is a branch of science that deals with collection, organization and analysis of data from the sample to the whole population. Moreover, it aids in designing a study more meticulously and also give a logical reasoning in concluding the hypothesis. Furthermore, biology study focuses on study of living organisms and their complex living pathways, which are very dynamic and cannot be explained with logical reasoning. However, statistics is more complex a field of study that defines and explains study patterns based on the sample sizes used. To be precise, statistics provides a trend in the conducted study.

Biological researchers often disregard the use of statistics in their research planning, and mainly use statistical tools at the end of their experiment. Therefore, giving rise to a complicated set of results which are not easily analyzed from statistical tools in research. Statistics in research can help a researcher approach the study in a stepwise manner, wherein the statistical analysis in research follows –

1. Establishing a Sample Size

Usually, a biological experiment starts with choosing samples and selecting the right number of repetitive experiments. Statistics in research deals with basics in statistics that provides statistical randomness and law of using large samples. Statistics teaches how choosing a sample size from a random large pool of sample helps extrapolate statistical findings and reduce experimental bias and errors.

2. Testing of Hypothesis

When conducting a statistical study with large sample pool, biological researchers must make sure that a conclusion is statistically significant. To achieve this, a researcher must create a hypothesis before examining the distribution of data. Furthermore, statistics in research helps interpret the data clustered near the mean of distributed data or spread across the distribution. These trends help analyze the sample and signify the hypothesis.

3. Data Interpretation Through Analysis

When dealing with large data, statistics in research assist in data analysis. This helps researchers to draw an effective conclusion from their experiment and observations. Concluding the study manually or from visual observation may give erroneous results; therefore, thorough statistical analysis will take into consideration all the other statistical measures and variance in the sample to provide a detailed interpretation of the data. Therefore, researchers produce a detailed and important data to support the conclusion.

Types of Statistical Research Methods That Aid in Data Analysis

Statistical analysis is the process of analyzing samples of data into patterns or trends that help researchers anticipate situations and make appropriate research conclusions. Based on the type of data, statistical analyses are of the following type:

1. Descriptive Analysis

The descriptive statistical analysis allows organizing and summarizing the large data into graphs and tables . Descriptive analysis involves various processes such as tabulation, measure of central tendency, measure of dispersion or variance, skewness measurements etc.

2. Inferential Analysis

The inferential statistical analysis allows to extrapolate the data acquired from a small sample size to the complete population. This analysis helps draw conclusions and make decisions about the whole population on the basis of sample data. It is a highly recommended statistical method for research projects that work with smaller sample size and meaning to extrapolate conclusion for large population.

3. Predictive Analysis

Predictive analysis is used to make a prediction of future events. This analysis is approached by marketing companies, insurance organizations, online service providers, data-driven marketing, and financial corporations.

4. Prescriptive Analysis

Prescriptive analysis examines data to find out what can be done next. It is widely used in business analysis for finding out the best possible outcome for a situation. It is nearly related to descriptive and predictive analysis. However, prescriptive analysis deals with giving appropriate suggestions among the available preferences.

5. Exploratory Data Analysis

EDA is generally the first step of the data analysis process that is conducted before performing any other statistical analysis technique. It completely focuses on analyzing patterns in the data to recognize potential relationships. EDA is used to discover unknown associations within data, inspect missing data from collected data and obtain maximum insights.

6. Causal Analysis

Causal analysis assists in understanding and determining the reasons behind “why” things happen in a certain way, as they appear. This analysis helps identify root cause of failures or simply find the basic reason why something could happen. For example, causal analysis is used to understand what will happen to the provided variable if another variable changes.

7. Mechanistic Analysis

This is a least common type of statistical analysis. The mechanistic analysis is used in the process of big data analytics and biological science. It uses the concept of understanding individual changes in variables that cause changes in other variables correspondingly while excluding external influences.

Important Statistical Tools In Research

Researchers in the biological field find statistical analysis in research as the scariest aspect of completing research. However, statistical tools in research can help researchers understand what to do with data and how to interpret the results, making this process as easy as possible.

1. Statistical Package for Social Science (SPSS)

It is a widely used software package for human behavior research. SPSS can compile descriptive statistics, as well as graphical depictions of result. Moreover, it includes the option to create scripts that automate analysis or carry out more advanced statistical processing.

2. R Foundation for Statistical Computing

This software package is used among human behavior research and other fields. R is a powerful tool and has a steep learning curve. However, it requires a certain level of coding. Furthermore, it comes with an active community that is engaged in building and enhancing the software and the associated plugins.

3. MATLAB (The Mathworks)

It is an analytical platform and a programming language. Researchers and engineers use this software and create their own code and help answer their research question. While MatLab can be a difficult tool to use for novices, it offers flexibility in terms of what the researcher needs.

4. Microsoft Excel

Not the best solution for statistical analysis in research, but MS Excel offers wide variety of tools for data visualization and simple statistics. It is easy to generate summary and customizable graphs and figures. MS Excel is the most accessible option for those wanting to start with statistics.

5. Statistical Analysis Software (SAS)

It is a statistical platform used in business, healthcare, and human behavior research alike. It can carry out advanced analyzes and produce publication-worthy figures, tables and charts .

6. GraphPad Prism

It is a premium software that is primarily used among biology researchers. But, it offers a range of variety to be used in various other fields. Similar to SPSS, GraphPad gives scripting option to automate analyses to carry out complex statistical calculations.

This software offers basic as well as advanced statistical tools for data analysis. However, similar to GraphPad and SPSS, minitab needs command over coding and can offer automated analyses.

Use of Statistical Tools In Research and Data Analysis

Statistical tools manage the large data. Many biological studies use large data to analyze the trends and patterns in studies. Therefore, using statistical tools becomes essential, as they manage the large data sets, making data processing more convenient.

Following these steps will help biological researchers to showcase the statistics in research in detail, and develop accurate hypothesis and use correct tools for it.

There are a range of statistical tools in research which can help researchers manage their research data and improve the outcome of their research by better interpretation of data. You could use statistics in research by understanding the research question, knowledge of statistics and your personal experience in coding.

Have you faced challenges while using statistics in research? How did you manage it? Did you use any of the statistical tools to help you with your research data? Do write to us or comment below!

Frequently Asked Questions

Statistics in research can help a researcher approach the study in a stepwise manner: 1. Establishing a sample size 2. Testing of hypothesis 3. Data interpretation through analysis

Statistical methods are essential for scientific research. In fact, statistical methods dominate the scientific research as they include planning, designing, collecting data, analyzing, drawing meaningful interpretation and reporting of research findings. Furthermore, the results acquired from research project are meaningless raw data unless analyzed with statistical tools. Therefore, determining statistics in research is of utmost necessity to justify research findings.

Statistical tools in research can help researchers understand what to do with data and how to interpret the results, making this process as easy as possible. They can manage large data sets, making data processing more convenient. A great number of tools are available to carry out statistical analysis of data like SPSS, SAS (Statistical Analysis Software), and Minitab.

nice article to read

Holistic but delineating. A very good read.

Rate this article Cancel Reply

Your email address will not be published.

Enago Academy's Most Popular Articles

• Promoting Research
• Thought Leadership
• Trending Now

How Enago Academy Contributes to Sustainable Development Goals (SDGs) Through Empowering Researchers

The United Nations Sustainable Development Goals (SDGs) are a universal call to action to end…

• Reporting Research

Research Interviews: An effective and insightful way of data collection

Research interviews play a pivotal role in collecting data for various academic, scientific, and professional…

Planning Your Data Collection: Designing methods for effective research

Planning your research is very important to obtain desirable results. In research, the relevance of…

• Language & Grammar

Best Plagiarism Checker Tool for Researchers — Top 4 to choose from!

While common writing issues like language enhancement, punctuation errors, grammatical errors, etc. can be dealt…

• Industry News
• Publishing News

2022 in a Nutshell — Reminiscing the year when opportunities were seized and feats were achieved!

It’s beginning to look a lot like success! Some of the greatest opportunities to research…

2022 in a Nutshell — Reminiscing the year when opportunities were seized and feats…

Sign-up to read more

Subscribe for free to get unrestricted access to all our resources on research writing and academic publishing including:

• 2000+ blog articles
• 50+ Webinars
• 10+ Expert podcasts
• 50+ Infographics
• 10+ Checklists
• Research Guides

We hate spam too. We promise to protect your privacy and never spam you.

I am looking for Editing/ Proofreading services for my manuscript Tentative date of next journal submission:

As a researcher, what do you consider most when choosing an image manipulation detector?

Statistics Made Easy

The Importance of Statistics in Research (With Examples)

The field of statistics is concerned with collecting, analyzing, interpreting, and presenting data.

In the field of research, statistics is important for the following reasons:

Reason 1 : Statistics allows researchers to design studies such that the findings from the studies can be extrapolated to a larger population.

Reason 2 : Statistics allows researchers to perform hypothesis tests to determine if some claim about a new drug, new procedure, new manufacturing method, etc. is true.

Reason 3 : Statistics allows researchers to create confidence intervals to capture uncertainty around population estimates.

In the rest of this article, we elaborate on each of these reasons.

Reason 1: Statistics Allows Researchers to Design Studies

Researchers are often interested in answering questions about populations like:

• What is the average weight of a certain species of bird?
• What is the average height of a certain species of plant?
• What percentage of citizens in a certain city support a certain law?

One way to answer these questions is to go around and collect data on every single individual in the population of interest.

However, this is typically too costly and time-consuming which is why researchers instead take a  sample  of the population and use the data from the sample to draw conclusions about the population as a whole.

There are many different methods researchers can potentially use to obtain individuals to be in a sample. These are known as  sampling methods .

There are two classes of sampling methods:

• Probability sampling methods : Every member in a population has an equal probability of being selected to be in the sample.
• Non-probability sampling methods : Not every member in a population has an equal probability of being selected to be in the sample.

By using probability sampling methods, researchers can maximize the chances that they obtain a sample that is representative of the overall population.

This allows researchers to extrapolate the findings from the sample to the overall population.

Read more about the two classes of sampling methods here .

Reason 2: Statistics Allows Researchers to Perform Hypothesis Tests

Another way that statistics is used in research is in the form of hypothesis tests .

These are tests that researchers can use to determine if there is a statistical significance between different medical procedures or treatments.

For example, suppose a scientist believes that a new drug is able to reduce blood pressure in obese patients. To test this, he measures the blood pressure of 30 patients before and after using the new drug for one month.

He then performs a paired samples t- test using the following hypotheses:

• H 0 : μ after = μ before (the mean blood pressure is the same before and after using the drug)
• H A : μ after < μ before (the mean blood pressure is less after using the drug)

If the p-value of the test is less than some significance level (e.g. α = .05), then he can reject the null hypothesis and conclude that the new drug leads to reduced blood pressure.

Note : This is just one example of a hypothesis test that is used in research. Other common tests include a one sample t-test , two sample t-test , one-way ANOVA , and two-way ANOVA .

Reason 3: Statistics Allows Researchers to Create Confidence Intervals

Another way that statistics is used in research is in the form of confidence intervals .

A confidence interval is a range of values that is likely to contain a population parameter with a certain level of confidence.

For example, suppose researchers are interested in estimating the mean weight of a certain species of turtle.

Instead of going around and weighing every single turtle in the population, researchers may instead take a simple random sample of turtles with the following information:

• Sample size  n = 25
• Sample mean weight  x  = 300
• Sample standard deviation  s = 18.5

Using the confidence interval for a mean formula , researchers may then construct the following 95% confidence interval:

95% Confidence Interval:  300 +/-  1.96*(18.5/√ 25 ) =  [292.75, 307.25]

The researchers would then claim that they’re 95% confident that the true mean weight for this population of turtles is between 292.75 pounds and 307.25 pounds.

Additional Resources

The following articles explain the importance of statistics in other fields:

The Importance of Statistics in Healthcare The Importance of Statistics in Nursing The Importance of Statistics in Business The Importance of Statistics in Economics The Importance of Statistics in Education

Featured Posts

Hey there. My name is Zach Bobbitt. I have a Masters of Science degree in Applied Statistics and I’ve worked on machine learning algorithms for professional businesses in both healthcare and retail. I’m passionate about statistics, machine learning, and data visualization and I created Statology to be a resource for both students and teachers alike.  My goal with this site is to help you learn statistics through using simple terms, plenty of real-world examples, and helpful illustrations.

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Join the Statology Community

Sign up to receive Statology's exclusive study resource: 100 practice problems with step-by-step solutions. Plus, get our latest insights, tutorials, and data analysis tips straight to your inbox!

By subscribing you accept Statology's Privacy Policy.

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Writing with Descriptive Statistics

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

Usually there is no good way to write a statistic. It rarely sounds good, and often interrupts the structure or flow of your writing. Oftentimes the best way to write descriptive statistics is to be direct. If you are citing several statistics about the same topic, it may be best to include them all in the same paragraph or section.

The mean of exam two is 77.7. The median is 75, and the mode is 79. Exam two had a standard deviation of 11.6.

Overall the company had another excellent year. We shipped 14.3 tons of fertilizer for the year, and averaged 1.7 tons of fertilizer during the summer months. This is an increase over last year, where we shipped only 13.1 tons of fertilizer, and averaged only 1.4 tons during the summer months. (Standard deviations were as followed: this summer .3 tons, last summer .4 tons).

Some fields prefer to put means and standard deviations in parentheses like this:

If you have lots of statistics to report, you should strongly consider presenting them in tables or some other visual form. You would then highlight statistics of interest in your text, but would not report all of the statistics. See the section on statistics and visuals for more details.

If you have a data set that you are using (such as all the scores from an exam) it would be unusual to include all of the scores in a paper or article. One of the reasons to use statistics is to condense large amounts of information into more manageable chunks; presenting your entire data set defeats this purpose.

At the bare minimum, if you are presenting statistics on a data set, it should include the mean and probably the standard deviation. This is the minimum information needed to get an idea of what the distribution of your data set might look like. How much additional information you include is entirely up to you. In general, don't include information if it is irrelevant to your argument or purpose. If you include statistics that many of your readers would not understand, consider adding the statistics in a footnote or appendix that explains it in more detail.

How to Write Statistics Research Paper | Easy Guide

A statistics research paper is an academic document presenting original findings or analyses derived from the data’s collection, organization, analysis, and interpretation. It addresses research questions or hypotheses within the field of statistics.

As a rule, college students get such papers assigned during a semester to assess their knowledge of statistics. However, any statistician specialist can also write research papers and publish them in academic journals, thus developing and promoting this field.

Want to master the art of statistics research paper writing?

We’ve got expert tips from a professional research paper writing service on crafting such studies. In this article, you’ll find a step-by-step guide on writing a statistics research paper that your educators, colleagues, or clients will approve.

How to write a statistics research paper: Steps

Table of Contents

State the problem

Collect the data, write an introductory paragraph, craft an abstract, describe your methodology, present your findings: evaluate and illustrate, revise and proofread.

Research papers aren’t about describing the existing knowledge on the topic. You should state your intellectual concern with it, indicating why it’s worth studying. When choosing the problem you’ll research in the paper, emphasize its ongoing nature:

What have other researchers already studied about it? Cite at least one previous publication related to your research and provide your statistical motivation to continue researching the topic. (You’ll refer to those researches in footnotes or within the text of your paper.)

Once you have the topic (problem) to research in your paper, it’s time to collect sources you’ll use as evidence and references. For statistics papers, consider the following:

• Published research from experts in Statistics (academic journals, newspapers, books, online publications, etc.)
• Statistical data from reliable sources (Google’s Public Data and Scholar, FedStats, and others)
• Your personal hypothesis, experiments, and info-gathering activities

The last one is a must-have! Your statistics research paper requires new information gathered by you as a researcher and not previously published anywhere. The massive block of your research paper will be about the data collection methods you used to investigate the problem and come to the conclusions you’ll provide.

Some underestimate the introductory paragraphs of research papers , but they are wrong. The introduction is the first thing a reader sees to understand if your research is worth their attention and time. With that in mind, ensure your introductory paragraph is intriguing yet informative enough for the audience to continue reading.

Start with a writing hook, a sentence grabbing a reader’s attention. Also, an intro needs background information: your topic and the scientific motivation for the new research methods. (What’s wrong with existing ones? Or, what do they miss?) Finally, move on to your thesis statement: 1-2 sentences summarizing the primary idea behind your research paper.

It’s an overview of your statistics research paper where you establish notation and outline the methods and the results. Abstracts are integral for all academic studies and research, giving readers enough details to decide whether your paper is relevant to them.

What do you include in an abstract?

Introduce your topic and explain why it’s significant in your field. State the gap present in the research at the moment and reveal the aim of your paper. Then, briefly describe your research methods and approach, summarize your findings, and explain their contribution to the field.

The methods section is the most extensive one in your research paper. Here, you provide sufficient information about how you collected data for your research, what methodologies you used, and how you evaluated the results.

Be specific; describe everything so the audience can repeat your research (experiments) and reconstruct your results. It’s the value your paper brings to the academic community.

Further paragraphs of your research paper present your findings. Try to stick to one idea per paragraph to make it clear and easy for readers to consume.

Prepare and add supporting materials that will help you illustrate findings: graphs, diagrams, charts, tables, etc. You can use them in a paper’s body or add them as an appendix; these elements will support your points and serve as extra proof for your findings.

Last but not least:

Write a concluding paragraph for your statistics research paper. Repeat your thesis, summarize your findings, and conclude whether they have proved or contradicted your initial theory (hypothesis). Also, you can make suggestions for further research in the same area.

Re-read your paper several times before publishing or submitting it for review. Ensure all the information is logical and coherent, all the terms are correct, and all the elements are present and accurately placed.

Also, proofread your final draft: Spelling, grammar, and punctuation mistakes are a no-no here! Re-check the list of references again; ensure you follow the required citation style and use the proper format.

So, now you know seven easy steps for writing a statistical research paper. Whether you’re a college student or a statistician willing to make a scientific contribution to a niche, follow them to craft a professionally structured academic document:

State a problem, choose methods of analyzing it, evaluate your findings, and illustrate them to engage the audience in discussion.

If you still need clarification or have questions about writing a statistics paper, don’t hesitate to ask for assistance. Professional writers with experience in statistics are ready to help you improve your writing skills.

Related Posts

Step by Step Guide on The Best Way to Finance Car

The Best Way on How to Get Fund For Business to Grow it Efficiently

• Youth Program
• Wharton Online

Research Papers / Publications

Log in using your username and password

• Search More Search for this keyword Advanced search
• Latest content
• Current issue
• BMJ Journals More You are viewing from: Google Indexer

You are here

• Volume 83, Issue 6
• EULAR recommendations for the management of psoriatic arthritis with pharmacological therapies: 2023 update
• Article Text
• Article info
• Citation Tools
• Rapid Responses
• Article metrics

• http://orcid.org/0000-0002-4528-310X Laure Gossec 1 , 2 ,
• http://orcid.org/0000-0002-6685-8873 Andreas Kerschbaumer 3 ,
• http://orcid.org/0000-0002-2517-0247 Ricardo J O Ferreira 4 , 5 ,
• http://orcid.org/0000-0003-2108-0030 Daniel Aletaha 3 ,
• http://orcid.org/0000-0002-9475-9362 Xenofon Baraliakos 6 ,
• Heidi Bertheussen 7 ,
• Wolf-Henning Boehncke 8 ,
• http://orcid.org/0000-0001-5331-8221 Bente Appel Esbensen 9 , 10 ,
• Iain B McInnes 11 ,
• Dennis McGonagle 12 , 13 ,
• http://orcid.org/0000-0002-3892-6947 Kevin L Winthrop 14 ,
• Andra Balanescu 15 ,
• Peter V Balint 16 ,
• http://orcid.org/0000-0001-7518-1131 Gerd R Burmester 17 ,
• http://orcid.org/0000-0003-2606-0573 Juan D Cañete 18 , 19 ,
• Pascal Claudepierre 20 , 21 ,
• http://orcid.org/0000-0002-1473-1715 Lihi Eder 22 ,
• http://orcid.org/0000-0003-4229-6818 Merete Lund Hetland 23 , 24 ,
• http://orcid.org/0000-0001-5592-724X Annamaria Iagnocco 25 ,
• Lars Erik Kristensen 26 , 27 ,
• Rik Lories 28 , 29 ,
• http://orcid.org/0000-0002-8418-7145 Rubén Queiro 30 , 31 ,
• http://orcid.org/0000-0002-9022-8863 Daniele Mauro 32 ,
• http://orcid.org/0000-0002-9683-3407 Helena Marzo-Ortega 12 , 13 ,
• http://orcid.org/0000-0002-6620-0457 Philip J Mease 33 , 34 ,
• http://orcid.org/0000-0002-2571-788X Peter Nash 35 ,
• Wendy Wagenaar 36 , 37 ,
• Laura Savage 38 ,
• http://orcid.org/0000-0001-8740-9615 Georg Schett 39 ,
• http://orcid.org/0000-0002-9441-5535 Stephanie J W Shoop-Worrall 40 ,
• http://orcid.org/0000-0002-0807-7139 Yoshiya Tanaka 41 ,
• http://orcid.org/0000-0002-3561-5932 Filip E Van den Bosch 42 ,
• Annette van der Helm-van Mil 43 ,
• http://orcid.org/0000-0002-0573-464X Alen Zabotti 44 ,
• http://orcid.org/0000-0002-5781-158X Désirée van der Heijde 43 ,
• Josef S Smolen 3
• 1 INSERM, Institut Pierre Louis d'Epidémiologie et de Santé Publique , Sorbonne Universite , Paris , France
• 2 APHP, Rheumatology Department , Hopital Universitaire Pitie Salpetriere , Paris , France
• 3 Division of Rheumatology, Department of Medicine 3 , Medical University of Vienna , Vienna , Austria
• 4 Nursing Research, Innovation and Development Centre of Lisbon (CIDNUR) , Higher School of Nursing of Lisbon , Lisbon , Portugal
• 5 Rheumatology Department , Centro Hospitalar e Universitário de Coimbra EPE , Coimbra , Portugal
• 6 Rheumazentrum Ruhrgebiet , Ruhr University Bochum , Herne , Germany
• 7 EULAR Patient Research Partner , EULAR , Oslo , Norway
• 8 Dermatology and Venereology , Geneva University Hospitals , Geneva , Switzerland
• 9 Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Centre for Head and Orthopaedics , Rigshospitalet , Glostrup , Denmark
• 10 Department of Clinical Medicine , University of Copenhagen , Copenhagen , Denmark
• 11 College of Medical Veterinary and Life Sciences , University of Glasgow , Glasgow , UK
• 12 LTHT , NIHR Leeds Biomedical Research Centre , Leeds , UK
• 13 Leeds Institute of Rheumatic and Musculoskeletal Medicine , University of Leeds , Leeds , UK
• 14 Division of Infectious Diseases, School of Medicine, School of Public Health , Oregon Health & Science University , Portland , Oregon , USA
• 15 Sf Maria Hospital , University of Medicine and Pharmacy Carol Davila Bucharest , Bucharest , Romania
• 16 Medical Imaging Centre, Semmelweis University, 3rd Rheumatology Department, National Institute of Musculoskeletal Diseases , Budapest , Hungary
• 17 Department of Rheumatology and Clinical Immunology, Freie Universität Berlin and Humboldt-Universität zu Berlin , Charité Universitätsmedizin Berlin , Berlin , Germany
• 18 Arthritis Unit, Department of Rheumatology , Hospital Clínic Barcelona , Barcelona , Spain
• 19 FCRB , IDIBAPS , Barcelona , Spain
• 20 Rheumatology , AP-HP, Henri Mondor University Hospital , Creteil , France
• 21 EA Epiderme , UPEC , Creteil , France
• 22 Department of Medicine, University of Toronto , Women's College Hospital , Toronto , Toronto , Canada
• 23 The Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Centre of Head and Orthopedics , Rigshospitalet Glostrup , Glostrup , Denmark
• 24 Department of Clinical Medicine, Faculty of Health and Medical Sciences , University of Copenhagen , Copenhagen , Denmark
• 25 Academic Rheumatology Centre, Dipartimento Scienze Cliniche Biologiche , Università di Torino - AO Mauriziano Torino , Turin , Italy
• 26 The Parker Institute , Bispebjerg , Denmark
• 27 Frederiksberg Hospital , Copenhagen University , Copenhagen , Denmark
• 28 Laboratory of Tissue Homeostasis and Disease, Skeletal Biology and Engineering Research Center , KU Leuven , Leuven , Belgium
• 29 Division of Rheumatology , University Hospitals Leuven , Leuven , Belgium
• 30 Rheumatology , Hospital Universitario Central de Asturias , Oviedo , Spain
• 31 Translational Immunology Division, Biohealth Research Institute of the Principality of Asturias , Oviedo University School of Medicine , Oviedo , Spain
• 32 Department of Precision Medicine , University of Campania Luigi Vanvitelli , Naples , Italy
• 33 Rheumatology Research , Providence Swedish , Seattle , Washington , USA
• 34 University of Washington School of Medicine , Seattle , Washington , USA
• 35 School of Medicine , Griffith University , Brisbane , Queensland , Australia
• 36 Tranzo, Tilburg School of Social and Behavioral Sciences , Tilburg University , Tilburg , The Netherlands
• 37 Young PARE Patient Research Partner , EULAR , Zurich , Switzerland
• 38 School of Medicine and Dermatology, Leeds Teaching Hospitals NHS Trust , University of Leeds , Leeds , UK
• 39 Department of Internal Medicine 3, Rheumatology and Immunology and Universitätsklinikum Erlangen , Friedrich-Alexander-Universität Erlangen-Nürnberg , Erlangen , Germany
• 40 Children and Young Person’s Rheumatology Research Programme, Centre for Musculoskeletal Research , The University of Manchester , Manchester , UK
• 41 First Department of Internal Medicine , University of Occupational and Environmental Health, Japan , Kitakyushu , Japan
• 42 Department of Internal Medicine and Pediatrics, VIB Center for Inflammation Research , Ghent University , Gent , Belgium
• 43 Rheumatology , Leiden University Medical Center , Leiden , The Netherlands
• 44 Department of Medical and Biological Sciences , Azienda sanitaria universitaria Friuli Centrale , Udine , Italy
• Correspondence to Laure Gossec, INSERM, Institut Pierre Louis d'Epidémiologie et de Santé Publique, Sorbonne Universite, Paris, France; laure.gossec{at}aphp.fr

Objective New modes of action and more data on the efficacy and safety of existing drugs in psoriatic arthritis (PsA) required an update of the EULAR 2019 recommendations for the pharmacological treatment of PsA.

Methods Following EULAR standardised operating procedures, the process included a systematic literature review and a consensus meeting of 36 international experts in April 2023. Levels of evidence and grades of recommendations were determined.

Results The updated recommendations comprise 7 overarching principles and 11 recommendations, and provide a treatment strategy for pharmacological therapies. Non-steroidal anti-inflammatory drugs should be used in monotherapy only for mild PsA and in the short term; oral glucocorticoids are not recommended. In patients with peripheral arthritis, rapid initiation of conventional synthetic disease-modifying antirheumatic drugs is recommended and methotrexate preferred. If the treatment target is not achieved with this strategy, a biological disease-modifying antirheumatic drug (bDMARD) should be initiated, without preference among modes of action. Relevant skin psoriasis should orient towards bDMARDs targeting interleukin (IL)-23p40, IL-23p19, IL-17A and IL-17A/F inhibitors. In case of predominant axial or entheseal disease, an algorithm is also proposed. Use of Janus kinase inhibitors is proposed primarily after bDMARD failure, taking relevant risk factors into account, or in case bDMARDs are not an appropriate choice. Inflammatory bowel disease and uveitis, if present, should influence drug choices, with monoclonal tumour necrosis factor inhibitors proposed. Drug switches and tapering in sustained remission are also addressed.

Conclusion These updated recommendations integrate all currently available drugs in a practical and progressive approach, which will be helpful in the pharmacological management of PsA.

• Psoriatic Arthritis
• Biological Therapy
• Biosimilar Pharmaceuticals

This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/ .

https://doi.org/10.1136/ard-2024-225531

Statistics from Altmetric.com

Request permissions.

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Introduction

Psoriatic arthritis (PsA) is a disease which has benefited from notable progress over recent years. Concepts have evolved, such as very early diagnosis and pre-PsA, as well as defining treatment targets and applying a holistic approach to comorbidity management. 1–4 Pharmacological options have extended, with the approval of new agents targeting various modes of action for PsA (as well as skin psoriasis). Drugs licensed for PsA now include (1) conventional synthetic (cs) disease-modifying antirheumatic drugs (DMARDs), such as methotrexate (MTX), sulfasalazine and leflunomide; (2) biological (b) DMARDs targeting tumour necrosis factor (TNF), the interleukin (IL)-12/23 or IL-23 pathway, and the IL-17A and IL-17A/F pathway; and (3) targeted synthetic (ts) DMARDs that inhibit Janus kinases (JAKs) or phosphodiesterase 4 (PDE4) ( table 1 ). 5 New safety data have emerged in inflammatory arthritis, particularly a worldwide cautionary comment regarding JAK inhibitors (JAKis), following a large randomised controlled trial (RCT) of tofacitinib in rheumatoid arthritis (RA). 6–8 Since the last EULAR recommendations for the pharmacological management of PsA in 2019, the field has changed significantly. 9–12 An update of the EULAR PsA management recommendations was therefore timely. 9

• View inline

Disease-modifying treatment options for psoriatic arthritis in 2023

This update addresses the non-topical, pharmacological management of PsA, with a specific focus on musculoskeletal (MSK) manifestations, while also addressing the spectrum of PsA, including how skin psoriasis, extra-MSK manifestations and comorbidities should influence treatment choices.

In accordance with the EULAR updated standardised operating procedures, 13 the process leading to this update included a data-driven approach and expert opinion.

After approval for an update by the EULAR Council in September 2022, taskforce members were selected by the convenor (JSS) and the methodologist (LG), to include more than one-third of new members, as well as country and gender representation. For the first time, experts from Australia, Japan and North America participated. Representatives from the health professionals in rheumatology (HPR) committee, patient research partners from PARE (People with Arthritis/Rheumatism) and young colleagues from the EMEUNET (EMerging EUlar NETwork) were included. Five members were recruited through an open call to EULAR countries via a competitive application process.

In October 2022, the steering group had its first meeting. The steering group consisted of seven rheumatologists (including the convenor, the methodologist and the fellow: JSS, LG, AK, DA, XB, IBM and DGM), a dermatologist (W-HB), an infectious disease specialist (KLW), an experienced fellow rheumatologist (AK), a patient research partner (HB) and two health professionals (BAE and RJOF, the latter acting in the capacity of a junior methodologist). Questions were then defined and addressed through a systematic literature review (SLR), performed by the fellow (AK) between November 2022 and April 2023, for the literature pertaining to pharmacological treatments of PsA and published since the previous SLR (ie, since the end of 2018). 5

The taskforce comprised the steering group and 23 other experts; members came from 19 different countries (of which 15 were EULAR countries), and included 27 rheumatology specialists, 2 dermatologists, 1 infectious disease specialist, 2 people affected with PsA acting as patient research partners, 2 HPRs and 3 rheumatology/epidemiology fellows/trainees. Overall, 47% of the taskforce members had not participated in the previous update in 2019. In April 2023, the taskforce met for a physical meeting to develop the updated bullet points. Each point was discussed in detail both in smaller (breakout) groups and in plenary sessions until consensus was reached. Group approval was sought through votes (by raised hands) for each bullet point; the limit for acceptance of individual recommendations was set at ≥75% majority among the taskforce for the first voting round; then (after discussions and potential reformulations) at ≥67% majority; and finally, if required, the last round of votes was accepted with >50% acceptance or else a proposal was rejected. 13

Although the SLR was a strong component of the discussions, the process was not only evidence-based but also experience-based and consensus-based, and included consideration of safety, efficacy, cost and long-term data. The levels of evidence (LoE) and grades of recommendation (GoR) were determined for each recommendation based on the Oxford Evidence Based System. 13 14 In May 2023, an anonymised email-based voting on the level of agreement (LoA) among the taskforce members was performed on a 0–10 scale (with 10 meaning full agreement) allowing calculation of mean LoA.

These recommendations address non-topical pharmacological treatments with a main focus on MSK manifestations. These recommendations concern stakeholders, such as experts involved in the care of patients with PsA, particularly rheumatologists and other health professionals (such as rheumatology nurses), general practitioners, dermatologists and other specialists; and also people with PsA as well as other stakeholders, for example, government and hospital officials, patient organisations, regulatory agencies and reimbursement institutions.

The overarching principles (OAPs) and recommendations are shown in table 2 , with LoE, GoR and LoA. The updated recommendations include 7 OAPs (vs 6 in 2019) and 11 recommendations (vs 12 in 2019, due to merges). Of the 11 recommendations, only 4 are unchanged compared with 2019 (the modifications compared with the 2019 recommendations are represented in table 3 ).

2023 updated EULAR recommendations for the pharmacological management of psoriatic arthritis

Comparison of the 2019 and 2023 EULAR recommendations for the management of psoriatic arthritis

Overarching principles

Of the seven OAPs, three remain unchanged, three were reworded and one has been added (overarching principle G). For more information on the thought process leading to the OAPs (unchanged or slightly changed), please refer to the 2015 and 2019 recommendations manuscripts. 9 15 Key points from the discussion of the OAPs are addressed in the following:

A. Psoriatic arthritis is a heterogeneous and potentially severe disease, which may require multidisciplinary treatment (unchanged) .

Although PsA is potentially severe, not all patients will develop severe forms. 16 17 Multidisciplinary management is helpful for many patients, through collaboration between physicians of different specialties and HPRs with the appropriate expertise. 18 19

B. Treatment of psoriatic arthritis patients should aim at the best care and must be based on a shared decision between the patient and the rheumatologist, considering efficacy, safety, patient preferences and costs.

This OAP was modified from 2019 to add patient preferences as an element to be considered and emphasise the importance of shared decision-making to maximise treatment adherence and efficacy while at the same time minimise complications driven by uncontrolled (active) disease as well as potential side effects of pharmacological drugs. 20 21

C. Rheumatologists are the specialists who should primarily care for the musculoskeletal manifestations of patients with psoriatic arthritis; in the presence of clinically relevant skin involvement, a rheumatologist and a dermatologist should collaborate in diagnosis and management.

We consider that rheumatology experts provide the best care for patients with PsA, given their experience with the many drugs used to treat these and other rheumatic and musculoskeletal diseases (RMDs), including the important aspects of safety and comorbidities. Consultation with dermatologists and sometimes other specialists may be helpful in individual clinical scenarios (see also overarching principles F and G). A very slight rewording was performed to discuss skin involvement as ‘clinically relevant’ rather than ‘clinically significant’ for more homogeneity with other bullet points. This bullet point does not address the role of HPRs, who are usually not prescribers in EULAR countries.

D. The primary goal of treating patients with psoriatic arthritis is to maximise health-related quality of life, through control of symptoms, prevention of structural damage, normalisation of function and social participation; abrogation of inflammation is an important component to achieve these goals (unchanged).

For more details, please see the 2019 update of these recommendations. 9

E. In managing patients with psoriatic arthritis, consideration should be given to each musculoskeletal manifestation and treatment decisions made accordingly (unchanged).

For more details, please refer to the 2019 update. 9

F. When managing patients with psoriatic arthritis, non-musculoskeletal manifestations (skin, eye and gastrointestinal tract) should be taken into account; comorbidities such as obesity, metabolic syndrome, cardiovascular disease or depression should also be considered.

The wording ‘such as obesity’ was added, since obesity is frequent in PsA and can influence outcomes. 22 23 Obesity concerns excess body fat, while metabolic syndrome is a collection of risk factors that increase the likelihood of developing cardiovascular disease and type 2 diabetes. Obesity is a significant contributor to the development of metabolic syndrome. The taskforce members discussed if other comorbidities should be added, but it was felt that the term ‘such as’ entails that comorbidities overall should be considered, without a need to list them. Depression and potentially other mental health issues may influence treatment choice. Central sensitisation to pain perception is frequent in PsA and also influences outcomes; this may lead to difficulties in disease management. 24 25 Bone health and malignancies were also specifically highlighted. The management of comorbidities poses specific issues, in particular as to who is responsible for managing distinct disease domains. Solutions need to be applied according to the individual patient, each country’s specific setting and healthcare system organisation.

G. The choice of treatment should take account of safety considerations regarding individual modes of action to optimise the benefit–risk profile (new).

Given new data on the safety of different modes of action, the taskforce proposed this new OAP to emphasise the importance of taking into account safety considerations for each patient. 6 The taskforce was aware that this item is somewhat redundant with overarching principle B but wished to emphasise the importance of benefit–risk assessment when considering the use of specific agents.

Recommendations

Of note, these recommendations are centred on non-topical pharmacological treatments; topical and non-pharmacological treatments are also important in PsA but are outside our scope. Figure 1 shows a summarised algorithm of the treatment proposals.

• Download figure
• Open in new tab
• Download powerpoint

2023 EULAR recommendations algorithm for the management of PsA. bDMARD, biological disease-modifying antirheumatic drug; csDMARD, conventional synthetic disease-modifying antirheumatic drug; IBD, inflammatory bowel disease; L, interleukin; JAK, Janus kinase inhibitor; JAKi, Janus kinase inhibitor; NSAID, non-steroidal anti-inflammatory drugs; TNF, tumour necrosis factor; TNFI, tumour necrosis factor inhibitor.

Some safety issues will be briefly addressed, but for a full picture of the adverse event profile of different drugs the package inserts should be consulted.

Recommendation 1

Treatment should be aimed at reaching the target of remission or, alternatively, low disease activity, by regular disease activity assessment and appropriate adjustment of therapy.

This (unchanged) recommendation is in keeping with the principles of treating-to-target. 26 27 Given the lack of new data to support treat-to-target in PsA, the LoE and GoR are also unchanged. The use of instruments to assess disease activity has been addressed in the treat-to-target recommendations. 26 The definition of remission in PsA remains a subject of debate. 28–30 For the context of these recommendations, remission should be seen as an abrogation of inflammation.

The taskforce members emphasised that disease activity should be regularly assessed across individual involved manifestations (eg, joints, skin, enthesitis, dactylitis, axial disease), and that treatment adjustments will depend on the predominant manifestation of the disease at a given moment. 31

Recommendation 2

Non-steroidal anti-inflammatory drugs may be used to relieve musculoskeletal signs and symptoms; local injections of glucocorticoids may be considered as adjunctive therapy.

This recommendation deals with the short-term use of symptomatic treatment. It was developed by merging the two previous recommendations 2 and 3, which dealt separately with non-steroidal anti-inflammatory drugs (NSAIDs) and glucocorticoids, as both only serve to relieve symptoms in the short term. It was decided to no longer allude to systemic glucocorticoids in a bullet point, since the data underlying the prescription of systemic glucocorticoids in PsA are scarce. Moreover, glucocorticoids harbour many potential safety issues, in particular when taking into account the high prevalence of comorbidities and cardiovascular risk factors in PsA. 3 32 However, the taskforce members agreed that, in some selected cases, systemic glucocorticoid therapy may be helpful for some patients, especially for polyarticular forms and/or as bridging therapy.

NSAIDs offer symptomatic relief to patients with MSK involvement, but have not shown any efficacy in psoriasis. NSAIDs and local glucocorticoid injections are useful to relieve symptoms and local inflammation temporarily, and may be used combined with DMARDs as needed (please see recommendation 3). However, the safety aspects of (potentially long-term) NSAID use have to be taken into account.

The taskforce emphasised that the vast majority of patients should not be treated with NSAIDs alone (without DMARDs), in keeping with a proactive treat-to-target approach to PsA. Only patients with very mild peripheral disease, or with predominant entheseal or axial disease, may sufficiently benefit from NSAIDs as monotherapy. Even in these cases, it is proposed that the use of symptomatic treatments alone should usually be short term, for example, limited to 4 weeks or so. In peripheral arthritis, this duration is based on the opinion of the group; in predominant axial disease, it is in keeping with the Assesment of Spondyloarthritis International Society (ASAS)/EULAR recommendations for axial spondyloarthritis (axSpA) whereby persistent disease after 4 weeks of treatment is considered a failure of NSAIDs. 33 On the other hand, for patients with predominant axial disease who experience significant improvement in clinical symptoms, continuous NSAID use may be proposed if needed to control symptoms, always taking the risks and benefits into account. Of note, data regarding the efficacy of NSAIDs in enthesitis are limited.

Recommendation 3

In patients with polyarthritis or those with monoarthritis/oligoarthritis and poor prognostic factors (eg, structural damage, elevated acute phase reactants, dactylitis or nail involvement), a csDMARD should be initiated rapidly, with methotrexate preferred in those with clinically relevant skin involvement.

Among patients with peripheral arthritis, 34 35 a distinction is made according to the number of swollen joints and according to prognostic factors. 36 In 2019, polyarthritis and monoarthritis/oligoarthritis with poor prognostic markers were addressed in separate bullet points, which were merged for clarity in this update ( table 3 ). Oligoarticular disease is defined as arthritis (swollen joints) of up to four (included) joints. 9 This definition applies to clinical detection (rather than imaging). The prognostic factors have also been previously defined 9 17 and are unchanged.

We recommend rapid csDMARD start, concomitant (or close) with the initiation of symptomatic therapy, for both patients with polyarticular disease and patients with oligoarticular disease and poor prognostic factors. Patients with oligoarticular disease and lack of poor prognostic factors should also receive a csDMARD, but there is less urgency for these patients given the more favourable long-term prognosis. The latter may receive csDMARDs after a longer delay, and potentially a period of symptomatic treatment alone (see recommendation 2). Since there is a lack of strong evidence to support this approach of rapid treatment introduction, this recommendation was mainly based on expert opinion.

Of note, there is no specific recommendation for dactylitis. We consider dactylitis as an association of (oligo)synovitis, tenosynovitis and enthesitis. Patients with isolated dactylitis should be treated similarly to patients with oligoarthritis; this includes the use of joint glucocorticoid injections and csDMARDs, which have shown efficacy in relieving dactylitis. 37

The first DMARD should be a csDMARD (meaning MTX, leflunomide or sulfasalazine). The decision concerning the first-line DMARD is important and led to much taskforce discussion, and has been put as an element for further research in the research agenda ( table 4 ). The continued prioritisation of csDMARDs reflects consensual expert opinion within the taskforce that favoured the benefit–risk–cost balance of csDMARDs and in particular MTX over targeted drugs. The absence of new data indicating the superiority of a b/tsDMARD as first-line, and in the presence of new data on MTX, was seen as confirming the efficacy of this drug in PsA. 5 37–39

Research agenda indicating priorities for future research in PsA

Since the EULAR recommendations adhere to a treat-to-target (T2T) approach which implies a reduction of disease activity by at least 50% within 3 months and reaching the treatment target within 6 months, a csDMARD should not be continued if these therapeutic goals are not attained. On csDMARD inefficacy, another DMARD, such as a bDMARD (see recommendation 4), can be rapidly instituted. Generally speaking, we recommend assessing the efficacy of the csDMARD and deciding if it should be pursued as monotherapy or not, after 12 weeks, in line with the T2T recommendations. 26 Although MTX use in PsA has typically been founded on evidence from other immune-mediated diseases such as RA and psoriasis, 40 there is also evidence for its efficacy in PsA, with recent confirmatory data both from observational data sources and from a randomised trial indicating that a proportion of patients will respond to escalation of doses of MTX. 39 41–43 The efficacy–safety balance of MTX should be assessed regularly, given the general metabolic profile of patients with PsA which can put them at a higher risk for adverse events such as hepatotoxicity. 42–44 The MTX dose should be sufficient, that is, usually between 20 mg and 25 mg weekly (about 0.3 mg/kg), and use of folate supplementation is recommended to reduce the adverse effects of MTX. 45

Other csDMARDs (ie, leflunomide and sulfasalazine) are potential treatment options and have demonstrated efficacy in PsA peripheral arthritis. 15 A recent trial of the combination of MTX with leflunomide indicated a low efficacy to safety ratio; thus, this association is not recommended. 38

Recommendation 4

In patients with peripheral arthritis and an inadequate response to at least one csDMARD, therapy with a bDMARD should be commenced.

This recommendation is relevant to patients with peripheral arthritis and therefore is meant to include both those with monoarticular/oligoarticular and those with polyarticular disease. However, where peripheral involvement is limited and without poor prognostic factors, it is not unreasonable to apply a second csDMARD course before initiating a bDMARD/tsDMARD, when this decision is agreed by the prescriber and the patient.

After failure of at least one csDMARD, the taskforce proposed as next step one of the many available bDMARDs ( table 1 ). 5

JAKi is efficacious in PsA, but the taskforce decided that at present the efficacy–safety balance, costs and long-term experience with many bDMARDs clearly favour their recommendation over JAKi. Relevant comorbidities in many patients with PsA also favour bDMARD selection.

Regarding bDMARDs, no order of preference is given since no bDMARD has demonstrated superiority for joint involvement over other bDMARDs ( table 1 ). 46–48 Herein they are listed in numeric order of the targeted cytokine, and not in order of preference. However, in the context of the present recommendation, CTLA4 (cytotoxic T-lymphocyte–associated antigen 4) inhibition is not considered a good option due to its limited efficacy in clinical trials. 49 The GoR is high for this bullet point, reflecting robust accrued data. 50

Unlike MSK manifestations, non-MSK domains of PsA allow differential order of bDMARD recommendation (se recommendation 9). 5 Two head-to-head trials of bDMARDs in PsA, both comparing an IL-17A inhibitor with adalimumab, showed similar efficacy for IL-17A inhibition and TNF inhibition, as regards efficacy on the joints, while skin responses are better with the former. 46 47 We also note that there is evidence on the better efficacy of a bDMARD compared with MTX in skin psoriasis (and evidence for differences between bDMARDs, please see recommendation 9). 51 52

All bDMARDs and JAKi showed efficacy regarding inhibition of radiographic progression; such data are lacking for apremilast.

The safety of the different available categories of bDMARDs appears acceptable in our SLR. 5 All bDMARDs increase the risk of infections. 5 The risks of TNF inhibitors (TNFis) are well known. Candidiasis (usually mucocutaneous) is more frequent with IL-17A and IL-17A/F inhibition, particularly the latter. 53 54 While IL-23-p19i is a more recent addition to the armament, its safety appears satisfactory, in line with ustekinumab which also interferes with IL-23 (p40 chain) whose adverse event profile is well known and appears satisfactory. 5

As a general rule, safety and comorbidities need to be taken into account when a decision to start a new drug is taken. More complete information regarding the safety aspects of bDMARDs is provided in the individual drug’s product information. Costs should also be taken into account, but these may vary at the country level; cost savings will occur in many countries due to the availability of biosimilar TNF blockers and potentially other biosimilars in due course. Personalised medicine, to facilitate an optimal choice of the first bDMARD, is currently difficult due to the lack of individualised predictors of response to treatment. 55 As previously discussed, it is of key importance to take into account the patient phenotype and potential extra-MSK features ( figure 1 ). Comorbidities are also to be considered. 23 56 More research is needed on the predictors of drug response, including the effect of sex. 57 58

Combination of a bDMARD with a csDMARD

First-line bDMARDs are often given in combination with csDMARDs, such as MTX. 41 59 However, there are conflicting data regarding the added benefit of concomitant MTX with targeted DMARDs in patients with peripheral disease and no evidence of a benefit of MTX in patients with axial symptoms. 33 60 61

MTX combination with bDMARDs has been explored mainly for TNFi; studies have generally found similar efficacy with or without concomitant MTX, although with increased drug survival when using MTX, in some studies. 41 59 62 A recent large study reported increased remission rates with TNFi plus MTX combination therapy. 59 With other modes of action, there is a lack of data to support comedication. Overall, the taskforce proposed to combine a first bDMARD with the previously prescribed csDMARD, in all cases where such a treatment has already been tolerated by the patient and in particular when the first bDMARD is a TNFi. For other modes of action, given the lack of data, we cannot recommend comedication, although the usual practice would be to continue a csDMARD when initiating a bDMARD (doses of the csDMARD can be diminished if needed).

Recommendation 5

In patients with peripheral arthritis and an inadequate response to at least one bDMARD, or when a bDMARD is not appropriate, a JAKi may be considered, taking safety considerations into account.

This recommendation elicited much debate. On the one hand, since 2019, new data have accrued on JAKis in terms of efficacy, such as the publication of positive trials on upadacitinib in PsA. 63 On the other hand, there is currently a worldwide cautionary statement issued by both the Food and Drug Administration and the European Medicine Agency restricting the use of JAKis in all diseases including PsA, based on an increased risk of cardiovascular and malignancy events observed with tofacitinib in older patients with RA with cardiovascular risk factors. 6–8 JAKis lead to increased general infection rates of similar magnitude to bDMARDs, but higher for herpes zoster infections. 5 Drug safety for the JAKis tofacitinib and upadacitinib in the specific context of PsA was recently reported and appeared reassuring; however, follow-up was short and further data are warranted. 64 65 While currently long-term extension data do not show increased cardiovascular/cancer risk related to JAKi use in PsA, there are no RCTs similar to the ORAL-Surveillance trial available at present in PsA. Therefore, the taskforce felt that the precautions related to RA also have to be taken for PsA, especially since various comorbidities important for the JAKi risk profile may be more prevalent in PsA than in RA (eg, obesity and cardiovascular risk factors). On the other hand, controlling inflammation is important to decrease cardiovascular risk.

Safety of JAKis should be carefully considered 66 ; we propose in table 2 and figure 1 a shortened version of the EMA warning/limitation to use, which includes age, smoking status and other cardiovascular/venous/cancer risk factors. 7 8

After much discussion, we considered that the efficacy–safety balance of JAKis did not justify putting JAKis on the same level as bDMARDs for order of choice (ie, proposing JAKis as usual treatment after insufficient response and/or intolerance to csDMARD treatment).

Therefore, JAKis are proposed usually as second-line targeted therapies (or third-line DMARDs). Of note, we recognise that, for some patients, JAKis may be a relevant option after a csDMARD; this is reflected in the wording of the bullet point (‘when a bDMARD is not appropriate’). This ‘non-appropriateness’ may include contraindications to bDMARDs, practical issues leading to a strong preference for oral administrations (eg, lack of proper conservation at regulated temperatures) and patient preferences, including risk of non-adherence to injections (in accordance with the first OAP concerning shared decision-making). Nevertheless, patients will have to weigh their preferences against potential risks.

The GoR was low for this recommendation, in particular regarding safety considerations, since the data are sparse in PsA and we had to rely on data taken from RA. The taskforce suggests using JAKi after bDMARDs have failed because several new bDMARDs with excellent effects on skin involvement and relatively good safety data are now available (IL-23, IL-17 inhibitors) and more long-term data on JAKi efficacy and safety are needed in PsA. The efficacy to safety ratio of JAKis was also put into the research agenda ( table 4 ).

Currently, drugs from the tyrosine kinase 2 (TYK2) pathway inhibition are being assessed in PsA 5 ; they are not currently licensed for use, and indeed the data are at this point limited in particular for safety (including in psoriasis where such therapy is licensed). Thus, we did not include TYK2 inhibition in the current recommendations.

Recommendation 6

In patients with mild disease and an inadequate response to at least one csDMARD, in whom neither a bDMARD nor a JAKi is appropriate, a PDE4 inhibitor may be considered.

This recommendation is unchanged from 2019, with unchanged LoE. ‘Mild disease’ is defined as oligoarticular or entheseal disease without poor prognostic factors and limited skin involvement. 9 67 The FOREMOST trial recently confirmed the efficacy of apremilast compared with placebo in oligoarticular PsA. 67 Nevertheless, the reason to place apremilast differently from bDMARDs or other tsDMARDs is not only based on its consistently relatively low efficacy, but also on the lack of structural efficacy data (thus putting the term ‘DMARD’ at risk since there are no data on inhibition of damage progression).

This recommendation received the lowest LoA within the taskforce, reflecting that more than a quarter of the taskforce participants were in favour of only discussing apremilast in the text without a specific bullet point.

The use of apremilast in combination with TNFi is off-label, and is a more costly drug combination with no supporting data and cannot be recommended.

Recommendation 7

In patients with unequivocal enthesitis and an insufficient response to NSAIDs or local glucocorticoid injections, therapy with a bDMARD should be considered.

This bullet point remains unchanged. Unequivocal enthesitis refers (as in 2019) to definite entheseal inflammation (which might need additional diagnostic imaging) to avoid overtreatment of entheseal pain not related to PsA (eg, in the context of widespread pain syndrome or repetitive mechanical stress). 68 69 In terms of treatment options, the taskforce discussed the recent data indicating indirectly some efficacy for MTX in enthesitis. 5 38 39 However, it was felt that the data for MTX were not sufficiently strong to propose MTX in the bullet point. We do acknowledge that, for some patients with enthesitis, MTX may be an option ( figure 1 ).

For unequivocal predominant enthesitis, the proposal is to introduce a bDMARD (without a preference for a specific mode of action) since all currently approved bDMARDs have demonstrated efficacy on enthesitis, with similar magnitudes of response, although head-to-head trials are missing ( figure 1 ). 5 Here, costs may be important, but other manifestations will also have to be taken into account (see recommendations 8 and 9). Of note, although tsDMARDs are not mentioned specifically in the bullet point, they are an option in some cases of enthesitis (always considering benefit to risk ratios, in particular for JAKis). 7 8

Recommendation 8

In patients with clinically relevant axial disease with an insufficient response to NSAIDs, therapy with an IL-17Ai, a TNFi, an IL-17 A/Fi or a JAKi should be considered.

The formulation for axial disease was modified from predominant to clinically relevant. For axial disease, in agreement also with the recently updated ASAS/EULAR axSpA recommendations, 33 we continue to judge csDMARDs as not relevant. bDMARDs targeting TNF and IL-17A and IL-17A/F as well as tsDMARDs targeting JAK are recommended. For JAKis, safety issues should be considered. Of note, we propose a choice between the drugs, not a combination of the drugs.

For this recommendation, the order of the drugs listed is of relevance, meaning that IL-17A inhibition has been put first due to the availability of currently only one trial specifically investigating axial PsA and using secukinumab (the MAXIMISE trial), 70 with the other drugs listed thereafter. Thus, the LoE is stronger for IL-17A inhibition than for the other drugs, where the data are derived from axial SpA. 33

The other drugs are listed with TNF inhibition first due to long-term safety data, then IL-17 A/F inhibition which has been recently licensed for axial SpA and JAK inhibition as an option taking into account safety. JAKis are here proposed in the same recommendation as bDMARDs, also reflecting that comorbidity profiles of patients with predominant or isolated axial PsA may be more comparable to patients with axial SpA and therefore may have a more favourable safety profile with respect to cardiovascular and cancer risks than many patients with predominant peripheral arthritis. The taskforce discussed the circumstantial evidence that IL-23 inhibition may be efficacious for axial PsA; however, given negative trials for IL-12/23 inhibition in axSpA, the IL-23 pathway is not recommended here. 33 71–73 Axial PsA remains a challenging form of PsA in terms of definition and differences with axial SpA; thus, this phenotype is part of the research agenda ( table 4 ).

Recommendation 9

The choice of the mode of action should reflect non-musculoskeletal manifestations related to PsA; with clinically relevant skin involvement, preference should be given to an IL-17A or IL-17A/F or IL-23 or IL-12/23 inhibitor; with uveitis to an anti-TNF monoclonal antibody; and with IBD to an anti-TNF monoclonal antibody or an IL-23 inhibitor or IL-12/23 inhibitor or a JAKi.

This is a new recommendation to clarify more visibly than in 2019 ( table 3 ) that the choice of drug should take into account not only the MSK PsA phenotype but also extra-MSK manifestations.

The first extra-MSK manifestation of interest in PsA is skin psoriasis. Although most patients with PsA present with skin psoriasis or have a personal history of skin psoriasis, registry data indicate that many patients with PsA have mild skin involvement. 74 However, even limited skin psoriasis can be troublesome, since relevant skin involvement is defined as either extensive (body surface area involvement >10%), or as important to the patient, that is, impacting negatively their quality of life (such as is the case with face or genital involvement). 9 For these patients, we recommend preferentially considering drugs targeting the IL-17A, IL-17A/F or IL-23 pathway (here, the order between drugs is cited in order of numbered cytokine, not preference). There are strong data, including head-to-head trials, in the field of skin psoriasis showing that drugs targeting the IL-23 and IL-17 pathways are superior to TNFis and to JAKis for skin psoriasis. 51 52 75–78 This justified proposing these modes of action preferentially in case of relevant skin involvement. This is in keeping with psoriasis recommendations. 79

Uveitis is not as frequent in PsA as it is in axial SpA; the prevalence is reported around 5%. 80 However, uveitis can be severe and should influence treatment decisions. Currently, the only mode of action with direct proof of efficacy on uveitis is TNF inhibition through monoclonal antibodies (ie, adalimumab and infliximab). Thus, for patients with uveitis, an anti-TNF monoclonal antibody is preferred.

Inflammatory bowel disease (IBD) concerns 2%–4% of patients with PsA. 80 The armamentarium for IBD has widened recently, and this recommendation reflects this fact, proposing that one of the modes of action currently licensed for IBD should be prescribed when it coexists with PsA. No order of preference is given here and prescribers are urged to adhere to EMA authorisations for IBD and take into account safety. For informative purposes, as of mid-2023, drugs authorised for IBD include anti-TNF monoclonal antibodies (ie, adalimumab and infliximab), the IL-12/23i ustekinumab, the IL-23i risankizumab (for Crohn’s disease) and two JAKis (one of which, tofacitinib, only for Crohn’s disease). 81–85 IL-17is (both A and A/F) are not recommended in case of active IBD, given indications of a heightened risk of flares. 86–88

Decisions for patients presenting with major skin involvement, with uveitis or with IBD should be discussed with the relevant specialist colleagues, as needed.

In all cases, the prescriber must refer to current drug authorisations and take into account safety and comorbidities.

To present an order for choosing drugs, we propose that the first element to take into account is the PsA subtype, then as a second element extra-MSK manifestations (always considering safety and comorbidities).

Recommendation 10

In patients with an inadequate response or intolerance to a bDMARD or a JAKi, switching to another bDMARD or JAKi should be considered, including one switch within a class.

This recommendation is unchanged from 2019, with unchanged LoE. 9 After failing one targeted drug, it is logical to switch to another targeted drug; there are currently no strong data to prefer a switch with a change in mode of action to a switch within the same mode of action. Of note, this recommendation does not limit the total number of switches for a given patient. It also does not necessarily mean that more switches within a class could not be done, but the taskforce felt that a switch should not necessarily be done after one drug of a class has failed. Switches can be made, as appropriate, between bDMARDs, or between bDMARDs and JAKis. We include abatacept as a treatment option ( table 1 ), 49 but note that it demonstrated modest efficacy and hence this is an option to be used only after failing one or more other targeted drugs. The efficacy of bimekizumab, the dual IL-17 A/F inhibitor, appeared similar in TNF-naïve and TNF-experienced populations; this will warrant confirmation. 53 54 Finally, a combination of bDMARDs is being explored, but cannot be recommended at this time.

Recommendation 11

In patients in sustained remission, tapering of DMARDs may be considered.

This bullet point is unchanged. However, more data have accrued on tapering, leading to a higher grade of recommendation. 89–91 By tapering we mean ‘dose reduction’ not drug discontinuation since the latter usually leads to flares. Drug tapering is a logical step when patients are doing well over time, from a safety and a cost perspective (tapering is often performed by the patient himself/herself alone). On the other hand, long-term data are missing and currently drug tapering is off-label. For all of these reasons, the taskforce kept the tentative wording of ‘may be considered’ (to ensure it is not made mandatory) and of course in the context of a shared decision with the patient (as is the case also for the other treatment decisions).

Research agenda

The taskforce felt that many issues needed more data, and an extensive research agenda was developed ( table 4 ).

This paper presents updated recommendations for the management of PsA, a treatment algorithm and a research agenda. This update addresses all currently available drugs and modes of action, and recommends an order to their use, taking into account the phenotype of the MSK and the non-MSK manifestations.

These elements should be helpful in the management of individual patients, but also in the advocacy for better access to care and for research.

This 2023 update is a major update since most of the recommendations were modified substantially. The EULAR standardised operating procedures propose a voting system for updates which discourages minor modifications for rewordings. 13 Since 2019, many new drugs have become available in PsA; the choice of which drug to prescribe to which patients rests on data related to efficacy, clinical phenotype, adverse event risk profile, tolerance, long-term data, cost and access. While laboratory biomarkers for stratified treatment approaches are lacking, the taskforce used clinical markers to develop clinical phenotypic preferences for specific drugs. In these updated recommendations, the taskforce applied expert opinion to the available data, to propose a pragmatic, logical order of a step-up approach to targeted treatments of PsA. The taskforce felt that proposing an order is helpful both for clinicians and to advocate for access to drugs for patients with PsA.

The drug options considered in these recommendations are currently licensed for PsA. We are aware that other drugs are being tested, or are available in other related conditions, especially skin psoriasis; however, these drugs are considered out of the scope of the present recommendations. Brodalumab was at the time of these recommendations only approved for psoriasis; TYK2 inhibitors such as deucravacitinib and brepocitinib have also been developed or in development for skin psoriasis and PsA; izokibep is a novel antibody mimetic, a small IL-17i currently undergoing testing; and an oral IL-23i is also in development. 5

The taskforce had extensive discussions on the positioning of JAKi in the recommendations. 63 92 We as a group feel that it is important to make haste slowly , and to uphold high safety standards when promoting drugs with only short-to-medium-term experience and for which long-term data are lacking—not least in PsA. In fact, this cautious attitude was also adhered to in the 2019 recommendations, and further safety developments have later confirmed that this attitude was appropriate. 7 8 It is of key importance to continue monitoring the drugs and, ideally, perform controlled trials, as only hard and high-level data can be reassuring.

Costs are also an important aspect in patient management, and it is generally recommended to prescribe the cheaper drug if two agents have similar efficacy and safety. Of note, even if one mode of action may have somewhat better efficacy on certain manifestations, a less expensive agent could still be preferred as long as it does not bear much lesser efficacy in that disease domain. Biosimilars are available for several TNFis and have led to significant reduction in expenditure and more use in many countries, while their price is not much lower than that of originators in many other ones. Tofacitinib will soon become generic, and the same is true for apremilast, which should also lower the costs for these agents and allow wider application especially in less affluent countries. Thus, overall, the taskforce felt that the prescription of drugs would account for the relationships between efficacy, safety and cost, in line with the OAPs and the 11 recommendations which are summarised in the algorithm ( figure 1 ). Many points are still to be confirmed in the management of PsA, leading to an extensive research agenda. 93

In conclusion, the updated 2023 recommendations should be helpful to clinicians but also to health professionals and patients when discussing treatment options. They can also be helpful to promote access to optimal care. As new data become available and new drugs are authorised in PsA, these recommendations should be again updated.

Ethics statements

Patient consent for publication.

Not required.

• Zabotti A ,
• De Marco G ,
• Gossec L , et al
• Alharbi S ,
• Lee K-A , et al
• Ferguson LD ,
• Siebert S ,
• McInnes IB , et al
• Lubrano E ,
• Scriffignano S ,
• de Vlam K , et al
• Kerschbaumer A ,
• Smolen JSS ,
• Ferreira JO , et al
• Ytterberg SR ,
• Mikuls TR , et al
• ↵ European Medicine Agency statement . Available : https://www.ema.europa.eu/en/medicines/human/referrals/janus-kinase-inhibitors-jaki [Accessed 7 Nov 2023 ].
• ↵ US food and Drug Administration . Available : https://www.fda.gov/safety/medical-product-safety-information/janus-kinase-jak-inhibitors-drug-safety-communication-fda-requires-warnings-about-increased-risk [Accessed 7 Nov 2023 ].
• Baraliakos X ,
• Kerschbaumer A , et al
• Coates LC ,
• Soriano ER ,
• Corp N , et al
• Ogdie A , et al
• ↵ Available : https://www.eular.org/web/static/lib/pdfjs/web/viewer.html?file=https://www.eular.org/document/download/680/b9eb08d0-faca-4606-8ed9-d0539b3f312a/660 [Accessed 1 Mar 2023 ].
• Chalmers I ,
• Glasziou P ,
• Greenhalgh T , et al
• Smolen JS ,
• Ramiro S , et al
• FitzGerald O ,
• Chandran V , et al
• Kerola AM ,
• Rollefstad S , et al
• Wendling D ,
• Hecquet S ,
• Fogel O , et al
• Gladman D ,
• McNeil HP , et al
• Chimenti MS ,
• Navarini L , et al
• Otero-Losada M ,
• Kölliker Frers RA , et al
• Orbai A-M , et al
• Trouvin AP ,
• Ballegaard C ,
• Skougaard M ,
• Guldberg-Møller J , et al
• Braun J , et al
• Moverley AR ,
• McParland L , et al
• Gayraud M , et al
• Landewé RBM ,
• van der Heijde D
• Orbai A-M ,
• Mease P , et al
• Vincken NLA ,
• Balak DMW ,
• Knulst AC , et al
• Nikiphorou E ,
• Sepriano A , et al
• de Vlam K ,
• Steinfeld S ,
• Toukap AN , et al
• Kishimoto M ,
• Deshpande GA ,
• Fukuoka K , et al
• Vieira-Sousa E ,
• Rodrigues AM , et al
• Mulder MLM ,
• Vriezekolk JE ,
• van Hal TW , et al
• Tillett W ,
• D’Agostino M-A , et al
• Bergstra SA , et al
• Lindström U ,
• di Giuseppe D ,
• Exarchou S , et al
• Wilsdon TD ,
• Whittle SL ,
• Thynne TR , et al
• Lambert De Cursay G ,
• Lespessailles E
• Curtis JR ,
• Beukelman T ,
• Onofrei A , et al
• Wang C , et al
• Behrens F , et al
• McInnes IB ,
• Behrens F ,
• Mease PJ , et al
• Bergmans P , et al
• Gottlieb AB ,
• van der Heijde D , et al
• Sawyer LM ,
• Markus K , et al
• Sbidian E ,
• Chaimani A ,
• Garcia-Doval I , et al
• Guelimi R , et al
• Asahina A ,
• Coates LC , et al
• Merola JF ,
• Landewé R ,
• Miyagawa I ,
• Nakayamada S ,
• Nakano K , et al
• Drosos GC ,
• Houben E , et al
• Tarannum S ,
• Leung Y-Y ,
• Johnson SR , et al
• Gorlier C , et al
• Di Giuseppe D ,
• Delcoigne B , et al
• Cañete JD ,
• Olivieri I , et al
• Rossmanith T ,
• Foldenauer AC , et al
• Fagerli KM ,
• Anderson JK ,
• Magrey M , et al
• Burmester GR ,
• Winthrop KL , et al
• Charles-Schoeman C ,
• Cohen S , et al
• Kristensen LE ,
• Yndestad A , et al
• Coates L , et al
• Lories RJ ,
• Marchesoni A ,
• Merashli M , et al
• Pournara E , et al
• Helliwell PS ,
• Gladman DD ,
• Chakravarty SD , et al
• Deodhar A ,
• Gensler LS ,
• Sieper J , et al
• Gladman DD , et al
• Love TJ , et al
• Bachelez H ,
• van de Kerkhof PCM ,
• Strohal R , et al
• Blauvelt A ,
• Bukhalo M , et al
• Reich K , et al
• Leonardi C ,
• Elewski B , et al
• Strober BE ,
• Kaplan DH , et al
• Harrison NL , et al
• Feagan BG ,
• Sandborn WJ ,
• Gasink C , et al
• Sands BE , et al
• Panaccione R , et al
• Vermeire S ,
• Zhou W , et al
• Loftus EV ,
• Lacerda AP , et al
• Letarouilly J-G ,
• Pierache A , et al
• Komaki Y , et al
• Tucker LJ ,
• Pillai SG ,
• Tahir H , et al
• Ruwaard J ,
• L’ Ami MJ ,
• Kneepkens EL , et al
• Fleishaker D , et al
• Widdifield J ,
• Wu CF , et al

Handling editor Dimitrios T Boumpas

X @LGossec, @FerreiraRJO, @lihi_eder, @dranielmar, @drpnash, @sshoopworrall

Contributors All authors have contributed to this work and approved the final version.

Funding Supported by EULAR (QoC016).

Competing interests No support to any author for the present work. Outside the submitted work: LG: research grants: AbbVie, Biogen, Lilly, Novartis, UCB; consulting fees: AbbVie, Amgen, BMS, Celltrion, Janssen, Lilly, MSD, Novartis, Pfizer, UCB; non-financial support: AbbVie, Amgen, Galapagos, Janssen, MSD, Novartis, Pfizer, UCB; membership on an entity’s Board of Directors or advisory committees: EULAR Treasurer. AK: speakers bureau, consultancy: AbbVie, Amgen, Galapagos, Janssen, Eli Lilly, MSD, Novartis, Pfizer, UCB. RJOF: research grants: Medac, Lilly; consulting fees: Sanofi. DA: research grants: Galapagos, Lilly; consulting fees: AbbVie, Gilead, Janssen, Lilly, Merck, Novartis, Sanofi. XB: research grants: AbbVie, MSD, Novartis; consultancies: AbbVie, Amgen, Celltrion, Chugai, Eli Lilly, Galapagos, Janssen, MSD, Novartis, Pfizer, Roche, Sandoz, UCB; membership on an entity’s Board of Directors or advisory committees: ASAS President, EULAR President Elect. W-HB: honoraria: AbbVie, Almirall, BMS, Janssen, Leo, Eli Lilly, Novartis, UCB; expert testimony: Novartis; participation on a Data Safety Monitoring Board or Advisory Board: AbbVie, Almirall, BMS, Janssen, Leo, Eli Lilly, Novartis, UCB. IBM: honoraria/consultation fees non-exec roles: NHS GGC Board Member, Evelo Board of Directors, Versus Arthritis Trustee Status; stock or stock options: Evelo, Cabaletta, Compugen, Causeway Therapeutics, Dextera. DGM: research grants: Janssen, AbbVie, Lilly, Novartis, UCB, BMS, Moonlake; consulting fees: Janssen, AbbVie, Lilly, Novartis, UCB, BMS, Moonlake, Celgene; honoraria: Janssen, AbbVie, Lilly, Novartis, UCB, BMS, Moonlake. KLW: research grants: BMS, Pfizer; consulting: Pfizer, AbbVie, AstraZeneca, BMS, Eli Lilly, Galapagos, GlaxoSmithKline (GSK), Gilead, Novartis, Moderna, Regeneron, Roche, Sanofi, UCB Pharma. AB: speakers fees: AbbVie, Amgen, AlphaSigma, AstraZeneca, Angelini, Biogen, BMS, Berlin-Chemie, Boehringer Ingelheim, Janssen, Lilly, MSD, Novartis, Pfizer, Roche, Sandoz, Teva, UCB, Zentiva; consultancies: Akros, AbbVie, Amgen, AlphaSigma, Biogen, Boehringer Ingelheim, Lilly, Mylan, MSD, Novartis, Pfizer, Roche, Sandoz, Sobi, UCB. PVB: consulting fees: AbbVie, Janssen-Cilag, Pfizer; honoraria: AbbVie, Bausch Health, Celltrion Healthcare, Eli Lilly, Gedeon Richter, IBSA Pharma, Infomed, Janssen-Cilag, Novartis, Pfizer, Sandoz; payment for expert testimony: Gedeon Richter; other: President, Hungarian Association of Rheumatologists. GRB: honoraria and/or speaker fees: AbbVie, BMS, Janssen, Lilly, Novartis, Pfizer. JDC: honoraria: UCB. PC: research grants: AbbVie, Amgen, Biogen, Jansen, Lilly, Novartis, UCB; consulting fees: AbbVie, Amgen, Celltrion, Janssen, Lilly, MSD, Novartis, Pfizer, UCB. LE: consultation fee/advisory board: AbbVie, Novartis, Janssen, UCB, BMS, Eli Lilly; research/educational grants: AbbVie, Fresenius Kabi, Janssen, Amgen, UCB, Novartis, Eli Lilly, Sandoz, Pfizer. MLH: grant support: AbbVie, Biogen, BMS, Celltrion, Eli Lilly, Janssen Biologics BV, Lundbeck Foundation, MSD, Pfizer, Roche, Samsung Bioepis, Sandoz, Novartis, Nordforsk; honoraria: Pfizer, Medac, Sandoz; advisory board: AbbVie; past-chair of the steering committee of the Danish Rheumatology Quality Registry (DANBIO, DRQ), which receives public funding from the hospital owners and funding from pharmaceutical companies; cochair of EuroSpA, partly funded by Novartis. AI: research grants from AbbVie, Pfizer, Novartis; honoraria for lectures, presentations, speakers bureaus from AbbVie, Alfasigma, BMS, Celgene, Celltrion, Eli Lilly, Galapagos, Gilead, Janssen, MSD, Novartis, Pfizer, Sanofi Genzyme, Sobi; EULAR Board Member; EULAR Congress Committee, Education Committee and Advocacy Committee Advisor; EULAR Past President. LEK: consultancies: AbbVie, Amgen, Biogen, BMS, Celgene, Eli Lilly, Pfizer, UCB, Sanofi, GSK, Galapagos, Forward Pharma, MSD, Novartis, Janssen; has been representing rheumatology FOREUM scientific chair. RQ: consultancy and/or speaker’s honoraria from and/or participated in clinical trials and/or research projects sponsored by AbbVie, Amgen-Celgene, Eli Lilly, Novartis, Janssen, Pfizer, MSD, UCB. DM: honoraria: UCB, Janssen, GSK, AstraZeneca, AbbVie; support to meetings: Janssen. HM-O: grant support: Janssen, Novartis, UCB; honoraria and/or speaker fees: AbbVie, Biogen, Eli Lilly, Janssen, Moonlake, Novartis, Pfizer, Takeda, UCB. PJM: grant support: AbbVie, Acelyrin, Amgen, Bristol Myers Squibb, Eli Lilly, Genascence, Janssen, Novartis, Pfizer, UCB; consulting fees: AbbVie, Acelyrin, Aclaris, Alumis, Amgen, Boehringer Ingelheim, Bristol Myers Squibb, Eli Lilly, Genascence, Inmagene, Janssen, Moonlake, Novartis, Pfizer, Takeda, UCB, Ventyx, Xinthera; honoraria: AbbVie, Amgen, Eli Lilly, Janssen, Novartis, Pfizer, UCB. PN: consulting fees and honoraria: AbbVie, Amgen, BMS, Lilly, Janssen, GSK, Novartis, UCB, Servatus; boards: Amgen, BMS, Janssen, GSK, Novartis, UCB; GRAPPA Steering Committee, Chair ASMPOC, ARA. LS: consulting fees: AbbVie, Almirall, Novartis, Janssen, Lilly, UCB, Pfizer, Bristol Myers Squibb, Boehringer Ingelheim; honoraria: AbbVie, Almirall, Novartis, Janssen, UCB, Pfizer, Takeda, Galderma, Biogen, Celgene, Celltrion, Lilly, Sanofi, Bristol Myers Squibb, Boehringer Ingelheim; support to attending meetings: AbbVie, Janssen, Lilly, Novartis, UCB, Galderma, Bristol Myers Squibb, Boehringer Ingelheim; participation in boards: AbbVie, Almirall, Novartis, Janssen, UCB, Pfizer, Galderma, Biogen, Lilly, Sanofi, Bristol Myers Squibb, Boehringer Ingelheim; GRAPPA Executive Board (elected), British Society for Medical Dermatology (BSMD) Committee. GS: honoraria: Novartis, Janssen. SJWS-W: grant support: Medical Research Council (MR/W027151/1). YT: research grants from Mitsubishi Tanabe, Eisai, Chugai, Taisho; speaking fees and/or honoraria from Eli Lilly, AstraZeneca, AbbVie, Gilead, Chugai, Boehringer Ingelheim, GlaxoSmithKline, Eisai, Taisho, Bristol Myers, Pfizer, Taiho. FEVdB: consultancy honoraria from AbbVie, Amgen, Eli Lilly, Galapagos, Janssen, Novartis, Pfizer, UCB. AZ: speakers bureau: AbbVie, Novartis, Janssen, Lilly, UCB, Amgen; paid instructor for AbbVie, Novartis, UCB. DvdH: consulting fees AbbVie, Argenx, Bayer, BMS, Galapagos, Gilead, GlaxoSmithKline, Janssen, Lilly, Novartis, Pfizer, Takeda, UCB Pharma; Director of Imaging Rheumatology bv; Associate Editor for Annals of the Rheumatic Diseases ; Editorial Board Member for Journal of Rheumatology and RMD Open ; Advisor Assessment Axial Spondyloarthritis International Society. JSS: research grants from AbbVie, AstraZeneca, Lilly, Galapagos; royalties from Elsevier (textbook); consulting fees from AbbVie, Galapagos/Gilead, Novartis-Sandoz, BMS, Samsung, Sanofi, Chugai, R-Pharma, Lilly; honoraria from Samsung, Lilly, R-Pharma, Chugai, MSD, Janssen, Novartis-Sandoz; participation in advisory board from AstraZeneca.

Provenance and peer review Not commissioned; externally peer reviewed.

Read the full text or download the PDF:

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
• Fam Med Community Health
• v.7(2); 2019

Basics of statistics for primary care research

Timothy c guetterman.

Family Medicine, University of Michigan, Michigan Medicine, Ann Arbor, Michigan, USA

The purpose of this article is to provide an accessible introduction to foundational statistical procedures and present the steps of data analysis to address research questions and meet standards for scientific rigour. It is aimed at individuals new to research with less familiarity with statistics, or anyone interested in reviewing basic statistics. After examining a brief overview of foundational statistical techniques, for example, differences between descriptive and inferential statistics, the article illustrates 10 steps in conducting statistical analysis with examples of each. The following are the general steps for statistical analysis: (1) formulate a hypothesis, (2) select an appropriate statistical test, (3) conduct a power analysis, (4) prepare data for analysis, (5) start with descriptive statistics, (6) check assumptions of tests, (7) run the analysis, (8) examine the statistical model, (9) report the results and (10) evaluate threats to validity of the statistical analysis. Researchers in family medicine and community health can follow specific steps to ensure a systematic and rigorous analysis.

Investigators in family medicine and community health often employ quantitative research to address aims that examine trends, relationships among variables or comparisons of groups (Fetters, 2019, this issue). Quantitative research involves collecting structured or closed-ended data, typically in the form of numbers, and analysing that numeric data to address research questions and test hypotheses. Research hypotheses provide a proposition about the expected outcome of research that may be assessed using a variety of methodologies, while statistical hypotheses are specific statements about propositions that can only be tested statistically. Statistical analysis requires a series of steps beginning with formulating hypotheses and selecting appropriate statistical tests. After preparing data for analysis, researchers then proceed with the actual statistical analysis and finally report and interpret the results.

Family medicine and community health researchers often limit their analyses to descriptive statistics—reporting frequencies, means and standard deviation (SD). While sometimes an appropriate stopping point, researchers may be missing opportunities for more advanced analyses. For example, knowing that patients have favourable attitudes about a treatment may be important and can be addressed with descriptive statistics. On the other hand, finding that attitudes are different (or not) between men and women and that difference is statistically significant may give even more actionable information to healthcare professionals. The latter question, about differences, can be addressed through inferential statistical tests. The purpose of this article is to provide an accessible introduction to foundational statistical procedures and present the steps of data analysis to address research questions and meet standards for scientific rigour. It is aimed at individuals new to research with less familiarity with statistics and may be helpful information when reading research or conducting peer review.

Foundational statistical techniques

Statistical analysis is a method of aggregating numeric data and drawing inferences about variables. Statistical procedures may be broadly classified into (1) statistics that describe data—descriptive statistics; and (2) statistics that make inferences about more general situations beyond the actual data set—inferential statistics.

Descriptive statistics

Descriptive statistics aggregate data that are grouped into variables to examine typical values and the spread of values for each variable in a data set. Statistics summarising typical values are referred to as measures of central tendency and include the mean, median and mode. The spread of values is represented through measures of variability, including the variance, SD and range. Together, descriptive statistics provide indicators of the distribution of data, or the frequency of values through the data set as in a histogram plot. Table 1 summarises commonly used descriptive statistics. For consistency, I use the terms independent variable and dependent variable, but in some fields and types of research such as correlational studies the preferred terms may be predictor and outcome variable. An independent variable influences, affects or predicts a dependent variable .

Inferential statistics: comparing groups with t tests and ANOVA

Inferential statistics are another broad category of techniques that go beyond describing a data set. Inferential statistics can help researchers draw conclusions from a sample to a population. 1 We can use inferential statistics to examine differences among groups and the relationships among variables. Table 2 presents a menu of common, fundamental inferential tests. Remember that even more complex statistics rely on these as a foundation.

Inferential statistics

The t test is used to compare two group means by determining whether group differences are likely to have occurred randomly by chance or systematically indicating a real difference. Two common forms are the independent samples t test, which compares means of two unrelated groups, such as means for a treatment group relative to a control group, and the paired samples t test, which compares means of related groups, such as the pretest and post-test scores for the same individuals before and after a treatment. A t test is essentially determining whether the difference in means between groups is larger than the variability within the groups themselves.

Another fundamental set of inferential statistics falls under the general linear model and includes analysis of variance (ANOVA), correlation and regression. To determine whether group means are different, use the t test or the ANOVA. Note that the t test is limited to two groups, but the ANOVA is applicable to two or more groups. For example, an ANOVA could examine whether a primary outcome measure—dependent variable—is significantly different for groups assigned to one of three different interventions. The ANOVA result comes in an F statistic along with a p value or confidence interval (CI), which tells whether there is some significant difference among groups. We then need to use other statistics (eg, planned comparisons or a Bonferroni comparison, to give two possibilities) to determine which of those groups are significantly different from one another. Planned comparisons are established before conducting the analysis to contrast the groups, while other tests like the Bonferroni comparison are conducted post-hoc (ie, after analysis).

Examining relationships using correlation and regression

The general linear model contains two other major methods of analysis, correlation and regression. Correlation reveals whether values between two variables tend to systematically change together. Correlation analysis has three general outcomes: (1) the two variables rise and fall together; (2) as values in one variable rise, the other falls; and (3) the two variables do not appear to be systematically related. To make those determinations, we use the correlation coefficient (r) and related p value or CI. First, use the p value or CI, as compared with established significance criteria (eg, p<0.05), to determine whether a relationship is even statistically significant. If it is not, stop as there is no point in looking at the coefficients. If so, move to the correlation coefficient.

A correlation coefficient provides two very important pieces of information—the strength and direction of the relationship. An r statistic can range from −1.0 to +1.0. Strength is determined by how close the value is to −1.0 or 1.0. Either extreme indicates a perfect relationship, while a value of 0 indicates no relationship. Cohen provides guidance for interpretations: 0.1 is a weak correlation, 0.3 is a medium correlation and 0.5 is a large correlation. 1 2 These interpretations must be considered in the context of the study and relative to the literature. The valence (+ or −) coefficient reveals the direction of the relationship. A negative correlation means one value rises, while the other tends to fall, and a positive coefficient means that the values of the two variables tend to rise and fall together.

Regression adds an additional layer beyond correlation that allows predicting one value from another. Assume we are trying to predict a dependent variable (Y) from an independent variable (X). Simple linear regression gives an equation (Y = b 0 + b 1 X) for a line that we can use to predict one value from another. The three major components of that prediction are the constant (ie, the intercept represented by b 0 ), the systematic explanation of variation (b 1 ), and the error, which is a residual value not accounted for in the equation 3 but available as part of our regression output. To assess a regression model (ie, model fit), examine key pieces of the regression output: (1) F statistic and its significance to determine whether the model systematically accounts for variance in the dependent variable; (2) the r square value for a measure of how much variance in the dependent variable is accounted for by the model; (3) the significance of coefficients for each independent variable in the model; and (4) residuals to examine random error in the model. Other factors, such as outliers, are potentially important (see Field 4 ).

The aforementioned inferential tests are foundational to many other advanced statistics that are beyond the scope of this article. Inferential tests rely on foundational assumptions, including that data are normally distributed, observations are independent, and generally that our dependent or outcome variable is continuous. When data do not meet these assumptions, we turn to non-parametric statistics (see Field 4 ).

A brief history of foundational statistics

Prominent statisticians Karl Pearson and Ronald A Fisher developed and popularised many of the basic statistics that remain a foundation for statistics today. Fisher’s ideas formed the basis of null hypothesis significance testing that sets a criterion for confidence or probability of an event. 4 Among his contributions, Fisher also developed the ANOVA. Pearson’s correlation coefficient provides a way to examine whether two variables are related. The correlation coefficient is denoted by r for a relationship between two variables or R for relationships among more than two variables as in multiple correlation or regression. 4 William Gosset developed the t distribution and later the t test as a way to examine whether two values of means were statistically different. 5

Statistical software

While the aforementioned statistics can be calculated manually, researchers typically use statistical software that process data, calculate statistics and p values, and supply a summary output from the analysis. However, the programs still require an informed researcher to run the correct analysis and interpret the output. Several available programs include SAS, Stata, SPSS and R. Try using the programs through a demonstration or trial period before deciding which one to use. It also helps to know or have access to others using the program should you have questions.

Example study

The remainder of this article presents steps in statistical analysis that apply to many techniques. A recently published study on communication skills to break bad news to a patient with cancer provides an exemplar to illustrate these steps. 6 In that study, the team examined the validity of a competence assessment of communication skills, hypothesising that after receiving training, post-test scores would be statistically improved from pretest scores on the same measure. Another analysis was to examine pretest sensitisation, tested through a hypothesis that a group randomly assigned to receive a pretest and post-test would not be significantly different from a post-test-only group. To test the hypotheses, Guetterman et al 6 examined whether mean differences were statistically significant by applying t tests and ANOVA.

Steps in statistical analysis

Statistical analysis might be considered in 10 related steps. These steps assume necessary background activities, such as conducting literature review and writing clear research question or aims, are already complete.

Step 1. Formulate a hypothesis to test

In statistical analysis, we test hypotheses. Therefore, it is necessary to formulate hypotheses that are testable. A hypothesis is specific, detailed and congruent with statistical procedures. A null hypothesis gives a prediction and typically uses words like ‘no difference’ or ‘no association’. 7 For example, we may hypothesise that group means on a certain measure are not significantly different and test that with an ANOVA or t-test. For example, in the exemplar study, one of the hypotheses was ‘MPathic-VR scores will improve (decreased score reflects better performance) from the preseminar test to the postseminar test based on exposure to the [breaking bad news] BBN intervention’ (p508), which was tested with a t test. 6 Hypotheses about relationships among variables could be tested with correlation and regression. Ultimately, hypotheses are driven by the purpose or aims of a study and further subdivide the purpose or aims into aspects that are specific and testable. When forming hypotheses, a concern is that having too many dependent variables leads to multiple tests of the same data set. This concern, called multiple comparisons or multiplicity, can inflate the likelihood of finding a significant relationship when none exists. Conducting fewer tests and adjusting the p value are ways to mitigate the concern.

Step 2. Select a test to run based on research questions or hypotheses

The statistical test must match the intended hypothesis and research question. Descriptive statistics allow us to examine trends limited to typical values, spread of values and distributions of data. ANOVAs and t tests are methods to test whether means are statistically different among groups and what those differences are. In the exemplar study, the authors used paired samples t-tests for pre–post scores with the same individuals and independent t tests for differences among groups. 6

Correlation is a method to examine whether two or more variables are related to one another, and regression extends that idea by allowing us to fit a line to make predictions about one variable based on a linear relationship to another. These statistical tests alone do not determine cause and effect, but merely associations. Causal inferences can only be made with certain research designs (eg, experiments) and perhaps with advanced statistical techniques (eg, propensity score analysis). Table 3 provides guidance for determining which statistical test to use.

Choosing and interpreting statistics for studies common in primary care

Step 3. Conduct a power analysis to determine a sample size

Before conducting analysis, we need to ensure that we will have an adequate sample size to detect an effect. Sample size relates to the concept of power. For example, to detect a small effect, a larger sample is needed. Larger sample sizes can thus detect a smaller effect. Sample size is determined through a power analysis. The determination of sample size is never a simple percent of the population, but a calculated number based on the planned statistical tests, significance level and effect size. 8 I recommend using G*Power for basic power calculations, although many other options are available. In the exemplar study, the authors did not report their power analysis prior to conducting the study, but they gave a post-hoc power analysis of the actual power based on their sample size and the effect size detected. 6

Step 4. Prepare data for analysis

Data often need cleaning and other preparation before conducting analysis. Problems requiring cleaning include values outside of an acceptable range and missing values. Any particular value could be wrong because of a data entry error or data collection problem. Visually inspecting data can reveal anomalies. For example, an age value of 200 is clearly an error, or a value of 9 on a 1–5 Likert-type scale is an error. An easy way to start inspecting data is to sort each variable by ascending values and then descending values to look for atypical values. Then, try to correct the problem by determining what the value should be. Missing values are a more complicated problem because a concern is why the value is missing. A few missing values at random is not necessarily a concern, but a pattern of missing values (eg, individuals from a specific ethnic group tend to skip a certain question) indicates a systematic missingness that could indicate a problem with the data collection instrument. Descriptive statistics are an additional way to check for errors and ensure data are ready for analysis. While not discussed in the communication assessment exemplar, the authors did prepare data for analysis and report missing values in their descriptive statistics.

Step 5. Always start with descriptive statistics

Before running inferential statistics, it is critical to first describe the data. Obtaining descriptive statistics is a way to check whether data are ready for further analysis. Descriptive statistics give a general sense of trends and can illuminate errors by reviewing frequencies, minimums and maximums that can indicate values outside of the accepted range. Descriptive statistics are also an important step to check whether we meet assumptions for statistical tests. In a quantitative study, descriptive statistics also inform the first table of the results that reports information about the sample, as seen in table 2 of the exemplar study. 6

Step 6. Check assumptions of statistical tests

All statistical tests rely on foundational assumptions. Although some tests are more robust to violations, checking assumptions indicates whether the test is likely to be valid for a particular data set. Foundational parametric statistics (eg, t tests, ANOVA, correlation, regression) assume independent observations and a normal linear distribution of data. In the exemplar study, the authors noted ‘Data from both groups met normality assumptions, based on the Shapiro–Wilk test’ (p508), and gave the statistics in addition to noting specific assumptions for the independent t tests around equality of variances. 6

Step 7. Run the analysis

Conducting the analysis involves running whatever tests were planned. Statistics may be calculated manually or using software like SPSS, Stata, SAS or R. Statistical software provides an output with key tests statistics, p values that indicate whether a result is likely systematic or random, and indicators of fit. In the exemplar study, the authors noted they used SPSS V.22. 6

Step 8. Examine how well the statistical model fits

The first step involves examining whether the statistical model was significant or a good fit. For t tests, ANOVAs, correlation and regression, first examine an overall test of significance. For a t test, if the t statistic is not statistically significant (eg, p>0.05 or a CI crossing 0), we can conclude no significant difference between groups. The communication assessment exemplar reports significance of the t tests along with measures such as equality of variance.

For an ANOVA, if the F statistic is not statistically significant (eg, p>0.05 or a CI crossing 0), we can conclude no significant difference between groups and stop because there is no point in further examining what groups may be different. If the F statistic is significant in an ANOVA, we can then use contrasts or post-hoc tests to examine what is different. For a correlation test, if the r value is not statistically significant (eg, p>0.05 or a CI crossing 0), we can stop because there is no point in looking at the magnitude or direction of the coefficient. If it is significant, we can proceed to interpret the r. Finally, for a regression, we can examine the F statistic as an omnibus test and its significance. If it is not significant, we can stop. If it is significant, then examine the p value of each independent variable and residuals.

Step 9. Report the results of statistical analysis

When writing statistical results, always start with descriptive statistics and note whether assumptions for tests were met. When reporting inferential statistical tests, give the statistic itself (eg, a F statistic), the measure of significance (p value or CI), the effect size and a brief written interpretation of the statistical test. The interpretation, for example, could note that an intervention was not significantly different from the control or that it was associated with improvement that was statistically significant. For example, the exemplar study gives the pre–post means along standard error, t statistic, p value and an interpretation that postseminar means were lower, along with a reminder to the reader that lower is better. 6

When writing for a journal, follow the journal’s style. Many styles italicise non-Greek statistics (eg, the p value), but follow the particular instructions given. Remember a p value can never be 0 even though some statistical programs round the p to 0. In that case, most styles prefer to report as p<0.001.

Step 10. Evaluate threats to statistical conclusion validity

Shadish et al 9 provide nine threats to statistical conclusion validity in drawing inferences about the relationship between two variables; the threats can broadly apply to many statistical analyses. Although it helps to consider and anticipate these threats when designing a research study, some only arise after data collection and analysis. Threats to statistical conclusion validity appear in table 4 . 9 Pertinent threats can be dealt with to the extent possible (eg, if assumptions were not met, select another test) and should be discussed as limitations in the research report. For example, in the exemplar study, the authors noted the sample size as a limitation but reported that a post-hoc power analysis found adequate power. 6

Threats to statistical conclusion validity

Key resources to learn more about statistics include Field 4 and Salkind 10 for foundational information. For advanced statistics, Hair et al 11 and Tabachnick and Fidell 12 provide detailed information on multivariate statistics. Finally, the University of California Los Angeles Institute for Digital Research and Education (stats.idre.ucla.edu/other/annotatedoutput/) provides annotated output from Stata, SAS, Stata and MPlus for many statistical tests to help researchers read the output and understand what it means.

Researchers in family medicine and community health often conduct statistical analyses to address research questions. Following specific steps ensures a systematic and rigorous analysis. Knowledge of these essential statistical procedures will equip family medicine and community health researchers with interpreting literature, reviewing literature and conducting appropriate statistical analysis of their quantitative data.

Nevertheless, I gently remind you that the steps are interrelated, and statistics is not only a consideration at the end of data collection. When designing a quantitative study, investigators should remember that statistics is based on distributions, meaning statistics works with aggregated numerical data and relies on variance within that data to test statistical hypotheses about group differences, relationships or trends. Statistics provides a broad view, based on these distributions, which brings implications at the early design phase. In designing a quantitative study, the nature of statistics generally suggests a larger number of participants in the research (ie, a larger n) to have adequate power to detect statistical significance and draw valid conclusions. Therefore, it will likely be helpful for researchers to include a biostatistician as early as possible in the research team when designing a study.

Contributors: The sole author, TCG, is responsible for the conceptualisation, writing and preparation of this manuscript.

Funding: This study was funded by the National Institutes of Health (10.13039/100000002) and grant number 1K01LM012739.

Competing interests: None declared.

Patient consent for publication: Not required.

Provenance and peer review: Not commissioned; internally peer reviewed.

• Future Annual Meetings
• 2024 Annual Meeting
• 2023 Annual Meeting
• 2022 Annual Meeting
• 2021 Annual Meeting
• April 19 AERA Gathering and Presidential Presentation
• 2019 Annual Meeting
• 2018 Annual Meeting
• 2017 Annual Meeting
• 2016 Annual Meeting
• 2015 Annual Meeting
• 2014 Annual Meeting
• Leveraged Knowledge and Cyclical Inequality
• Demonizing the Undeserving Poor
• Does that Sound Like Meritocracy to You?
• A Global “HEADS UP”
• What’s Race Got to Do with It
• Education Policy is Social Policy
• Reading History and Learning about Policy and Peop
• Poverty and Impoverishment in the Bay Area of Cali
• Poverty and Education: Reflections on the AERA Con
• Trying to Fix an Urban School - 2013 AM Theme
• The Poverty of Capitalism
• Myth of Poverty
• On Poverty and Systemic Collapse
• Poverty has an iPhone
• Media at Annual Meeting
• 2012 Annual Meeting
• 2011 Annual Meeting
• Past Brown Lectures
• Virtual Events
• AERA Centennial
• Webcasts of Lectures & Events

Share 

• Harvard Medical School
• HMS Scholarly Articles
• Communities & Collections
• By Issue Date
• FAS Department
• Quick submit
• Waiver Generator
• DASH Stories
• Accessibility
• COVID-related Research

Terms of Use

• Privacy Policy
• By Collections
• By Departments

IG# & IG% in Upper Urinary Tract Infection with Sirs Syndrome Diagnosis, a Retrospective Research at Binh Dan Hospital

Access Status

Published version, citable link to this page, collections.

• HMS Scholarly Articles [17928]

Contact administrator regarding this item (to report mistakes or request changes)