To the Editor.—
The article by Hayden et al (1982;247:326-331) on the methodology of the case-control study contains a factual error in describing articles published previously.1,2 They report that in two studies of reserpine and breast cancer, "patients with thyrotoxicosis, renal disease, or cardiovascular disease were excluded from the control, non-breast-cancer groups..." This statement is incorrect. Such patients were excluded from the control group only if these diseases caused admission. All other control patients with such diseases were, of course, included. The same criteria were applied to the case group—namely, women were excluded if they came into the hospital because of thyroid or cardiovascularrenal disease.The principle involved in such studies is that the same criteria for exclusion must be applied to both cases and control subjects.3 In the matter of reserpine and breast cancer, it should be obvious to even someone without formal epidemiologic training that if
Jick H. Case-Control Studies. JAMA. 1982;248(5):546–547. doi:10.1001/jama.1982.03330050030016
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: