The case-control study design is deceptively simple. However, many design considerations influence the estimated effect measure. An investigation of case-control studies in the human health literature suggested that some of these considerations are not described in reports of case-control studies. Our hypothesis was that the majority of veterinary studies labeled as case-controls would be incident density designs, and many would not interpret the effect measure obtained from those studies as the rate ratio rather than the odds ratio. Reference databases were searched for author-designated case-control studies. A survey of 100 randomly selected studies was conducted to examine the different design options described and estimated effect measures. Of the 100 author-identified case-control studies, 83 assessed an exposure-outcome association and, of those, only 54 (65.1%) sampled the study population based on an outcome and would thus be considered case-control designs. Twelve studies were incidence density designs but none used this terminology. Of the studies that reported an odds ratio as the effect measure, none reported on additional considerations that would have enabled a more interpretable result. This survey indicated many case-control-labeled studies were not case-control designs and among case-control studies, key design aspects were not often described. The absence of information about study design elements and underlying assumptions in case-control studies limits the ability to establish the effect measured by the study and the evidentiary value of the study might be underestimated.
Keywords: Case-control; Inference; Retrospective; Study design.
Copyright © 2016 Elsevier B.V. All rights reserved.