1998/03/28 by Huw Davies, Iain K. Crombie, M. Tavakoli · 990 citations
Medicine · Social Sciences · Health Professions · #Neonatal Respiratory Health Research #Delphi Technique in Research #Health and Conflict Studies #Odds #Computer science #Medicine #Data science #Machine learning #Logistic regression
paper · open access · doi:10.1136/bmj.316.7136.989
published in BMJ 316(7136), 989-991
openalex publication_date 1998/03/28 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/25
Odds ratios are a common measure of the size of an effect and may be reported in case-control studies, cohort studies, or clinical trials. Increasingly, they are also used to report the findings from systematic reviews and meta-analyses. Odds ratios are hard to comprehend directly and are usually interpreted as being equivalent to the relative risk. Unfortunately, there is a recognised problem that odds ratios do not approximate well to the relative risk when the initial risk (that is, the prevalence of the outcome of interest) is high. 1 2 Thus there is a danger that if odds ratios are interpreted as though they were relative risks then they may mislead. The advice given in many texts is unusually coy on the matter. For example: “The odds ratio is approximately the same as the relative risk if the outcome of interest is rare. For common events, however, they can be quite different.”3 How close is “approximately the same,” how uncommon does an event have to be to qualify as “rare,” and how different is “quite different”? #### Summary points If the odds ratio is interpreted as a relative risk it will always overstate any effect size: the odds ratio is smaller than the relative risk for odds ratios of less than one, and bigger than the relative risk for odds ratios of greater than one The extent of overstatement increases as both the initial risk increases and the odds ratio departs from unity However, serious divergence between the odds ratio and the relative risk occurs only with large effects on groups at high initial risk. Therefore qualitative judgments based on interpreting odds ratios as though they were relative risks are unlikely to be seriously in error In studies which show reductions in risk (odds ratios of less than one), the odds ratio …