Editing Case–control study (section)

===Control group selection===
Controls need not be in good health; inclusion of sick people is sometimes appropriate, as the control group should represent those at risk of becoming a case.<ref name="Grimes_2005"/> Controls should come from the same population as the cases, and their selection should be independent of the exposures of interest.<ref name="pmid11844534">{{cite journal |vauthors=Schulz KF, Grimes DA | title = Case–control studies: research in reverse | journal = Lancet | volume = 359 | issue = 9304 | pages = 431–4 | year = 2002 | pmid = 11844534 | doi = 10.1016/S0140-6736(02)07605-5 | s2cid = 10770936 }}</ref>

Controls can carry the same disease as the experimental group, but of another grade/severity, therefore being different from the outcome of interest. However, because the difference between the cases and the controls will be smaller, this results in a lower [[statistical power|power]] to detect an exposure effect.{{citation needed|date=May 2023}}

As with any epidemiological study, greater numbers in the study will increase the power of the study. Numbers of cases and controls do not have to be equal. In many situations, it is much easier to recruit controls than to find cases. Increasing the number of controls above the number of cases, up to a ratio of about 4 to 1, may be a cost-effective way to improve the study.<ref name="Grimes_2005">{{cite journal |vauthors=Grimes DA, Schulz KF | title = Compared to what? Finding controls for case–control studies | journal = Lancet | volume = 365 | issue = 9468 | pages = 1429–33 | year = 2005 | pmid = 15836892 | doi = 10.1016/S0140-6736(05)66379-9 | s2cid = 836985 }}</ref>