An odd measure of risk: use and misuse of the odds ratio

Abstract

Objective: To determine how often the odds ratio, as used in clinical research of obstetrics and gynecology, differs substantially from the risk ratio estimate and to assess whether the difference in these measures leads to misinterpretation of research results.

Methods: Articles from 1998 through 1999 in Obstetrics & Gynecology and the American Journal of Obstetrics and Gynecology were searched for the term "odds ratio." The key odds ratio in each article was identified, and, when possible, an estimated risk ratio was calculated. The odds ratios and the estimated risk ratios were compared quantitatively and graphically.

Results: Of 151 studies using odds ratios, 107 were suitable to estimate a risk ratio. The difference between the odds ratio and the estimated risk ratio was greater than 20% in 47 (44%) of these articles. An odds ratio appears to magnify an effect compared with a risk ratio. In 39 (26%) articles the odds ratio was interpreted as a risk ratio without explicit justification.

Conclusion: The odds ratio is frequently used, and often misinterpreted, in the current literature of obstetrics and gynecology.