Advanced statistics: up with odds ratios! A case for odds ratios when outcomes are common

Abstract

Treatment comparisons from clinical studies involving dichotomous outcomes are often summarized using risk ratios. Risk ratios are typically used because the underlying statistical model is often consistent with the underlying biological mechanism of the treatment and they are easily interpretable. The use of odds ratios to summarize treatment effects has been discouraged, especially in studies in which outcomes are common, largely because odds ratios differ from risk ratios and are frequently interpreted incorrectly as risk ratios. In this article, the author contends that risk ratios can be easily misinterpreted and that, in many cases, odds ratios should be preferred, especially in studies in which outcomes are common.