Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

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.

Https

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.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2009 Mar-Apr;58(2):123-7.
doi: 10.1097/NNR.0b013e318199b517.

Simpson's paradox and experimental research

Suzanne Ameringer  1 , Ronald C Serlin, Sandra Ward
Affiliations
Review

Simpson's paradox and experimental research

Suzanne Ameringer et al. Nurs Res. 2009 Mar-Apr.

Abstract

Background: Experimental research in nursing has increased considerably in recent years. To improve the quality of such research, it is critical to reduce threats to internal validity. One threat that has received inadequate attention in the nursing literature is Simpson's paradox--a case of extreme confounding that can lead to erroneous conclusions about the effects of an experimental intervention. In fact, it can lead to a conclusion about an intervention effect that is the opposite of the correct inference.

Approach: The aims of this study were to describe Simpson's paradox, provide a hypothetical example, and discuss approaches to avoiding the paradox.

Results: The paradox is due to the combination of an overlooked confounding variable and a disproportionate allocation of that variable among experimental groups. Different designs and analysis approaches that can be used to avoid the paradox are presented.

Discussion: Simpson's paradox can be avoided by selecting an appropriate experimental design and analysis that incorporates the confounding variable in such a way as to obtain unconfounded estimates of treatment effects, thus more accurately answering the research question.

PubMed Disclaimer

References

    1. Altman DG, Schulz KF, Moher D, Egger M, Davidoff F, Elbourne D, et al. The Revised CONSORT statement for reporting randomized trials: Explanation and elaboration. Annals of Internal Medicine. 2001;134(8):663–694. - PubMed
    1. Appleton DR, French JM, Vanderpump MPJ. Ignoring a covariate: An example of Simpson's paradox. The American Statistician. 1996;50(44):340–341.
    1. Cohen J. “New-look” multiple regression/correlation analysis and the analysis of variance/covariance. In: Keren G, editor. Statistical and methodological issues in psychology and social sciences research. Erlbaum Associates; Hillsdale, NJ: 1982. pp. 41–69.
    1. Cornfield J, Haenszel W, Hammond EC, Lilienfeld AM, Shimkin MB, Wynder EL. Smoking and lung cancer: Recent evidence and a discussion of some questions. Journal of the National Cancer Institute. 1959;22(1):173–203. - PubMed
    1. Hintzman DL. Simpson's paradox and the analysis of memory retrieval. Psychological Review. 1980;87(4):398–410.