What is so odd about odds

摘要: In clinical studies, the relative likelihood of an event occurring between 2 groups is often expressed as risk ratio (RR) or odds (OR). The RR intuitive parameter that relatively easy to interpret. Quantitative interpretation OR much more difficult and incorrectly equated RR. problem may differ substantially from RR, especially when outcome interest common in study population. This article explains clarifies controversial issues surrounding use OR. Theoretical concepts relating ORs are illustrated by examples surgical literature. By reviewing articles 5 journals over a 5-year period, we show presented misinterpreted equivalent When discrepancy large, using uncritically estimate will strongly bias inferences about treatment effect cause disease amplifying apparent strength association exposure outcome.