Comparability and the Case-Control Study

Ezra Susser, Sharon Schwartz, Alfredo Morabia and Evelyn J. Bromet

in Psychiatric Epidemiology

Published in print July 2006 | ISBN: 9780195101812
Published online September 2009 | e-ISBN: 9780199864096 | DOI:

Series: Oxford Psychiatry Series

Comparability and the Case-Control Study

More Like This

Show all results sharing these subjects:

  • Public Health and Epidemiology
  • Medical Statistics and Methodology


Show Summary Details


The validity of a case-control study depends upon sampling controls from the noncases in an unbiased way, that is, independent of exposure status. Although this safeguard will prevent introducing bias when the controls are selected, any bias already present in the underlying cohort will still be reflected in the case-control study. When the exposed and unexposed groups in the underlying cohort are not fully comparable, the resulting odds ratio will not reflect the causal effect of the exposure. It will be biased. In general, bias are handled in parallel fashion for cohort and case-control studies. But the logical connections between the problem and its resolution are more difficult to see in the context of the case-control design. This chapter explains these connections and their practical implications for the selection of controls. It discusses in turn the main sources of noncomparability: confounding, unequal attrition, and differential misclassification. It uses the nested case-control study to portray a logic that in large part also applies to the ordinary case-control study.

Keywords: case-control studies; noncomparability; confounding; unequal attrition; differential misclassification; nested case-control study

Chapter.  5945 words. 

Subjects: Public Health and Epidemiology ; Medical Statistics and Methodology

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.