METHODOLOGIC STANDARDS AND CONTRADICTORY RESULTS IN CASE-CONTROL RESEARCH

Despite a reversal of the customary direction of the cause → effect reasoning used in prospective (cohort) studies, the retrospective case-control method for the study of disease etiology has become epidemiologically popular and sanctioned by authorities who claim that it rarely produces contradictory results. Nevertheless, we have found at least 17 topics in which conflicts were noted in conclusions that arose either among case-control studies or between case-control and cohort studies of the same topic. The 17 topics include the etiologic relationships of myocardial infarction to coffee-drinking and aspirin, and of various neoplastic diseases to reserpine, estrogens, coffee-drinking, herpesvirus, oral contraceptives, appendectomy, tonsillectomy, prenatal irradiation, benign prostatic hyperplasia, asthma, circumcision, early age of menarche and tuberculosis. The 85 case-control investigations of these topics were each evaluated for the fulfillment of 11 methodologic standards that would enhance scientific quality in the research. The standards include a predetermined method of patient selection, clear specification of the risk agent, unbiased collection of data, efforts to provide anamnestic equivalence, avoidance of constrained selection for cases and controls, equal diagnostic examination, equal prehospital surveillance, equal demographic and clinical susceptibility, and avoidance of protopathic bias in the compared groups. These standards, which were commonly violated in the 85 reviewed investigations, should not be used to provide a general summary score for individual studies, since the impact of each type of violation depends on the topic under investigation and must be appraised separately for that topic. Certain scientific problems of case-control studies are inherent in the research architecture, but others can be eliminated or reduced by better attention to the quality of the conventional research procedures and by special new methods of sampling and analysis. The cited standards can help readers to evaluate the results of casecontrol research and can help designers of future studies to improve their scientific structure and credibility. © 1979.