Choosing the Right Measure of Effect: Guidance for Authors Reporting Binary Outcomes

When reporting differences in the incidence or proportion of a binary outcome between groups, common measures include absolute risk difference, relative risk (RR), and odds ratio (OR). For studies in which the primary outcome is a difference in proportions between two groups, Prehospital and Disaster Medicine prioritizes the absolute risk difference as the principal measure of effect, accompanied by a 95% confidence interval and P-value. Relative risk may be reported secondarily when appropriate. Odds ratios should generally be avoided as they are frequently misinterpreted and may exaggerate the apparent magnitude of an effect. Odds ratios should be limited to situations in which they are required by the selected statistical method.