PURPOSE: In cohort studies of common outcomes, odds ratios (ORs) may seriously overestimate the true effect of an exposure on the outcome of interest (as measured by the risk ratio [RR]). Since few study designs require ORs (most frequently, case-control studies), their popularity is due to the widespread use of logistic regression. Because ORs are used to approximate RRs so frequently, methods have been published in the general medical literature describing how to convert ORs to RRs; however, these methods may produce inaccurate confidence intervals (CIs). The authors explore the use of binomial regression as an alternative technique to directly estimate RRs and associated CIs in cohort studies of common outcomes. METHODS: Using actual study data, the authors describe how to perform binomial regression using the SAS System for Windows, a statistical analysis program widely used by US health researchers. RESULTS: In a sample data set, the OR for the exposure of interest overestimated the RR more than twofold. The 95% CIs for the OR and converted RR were wider than for the directly estimated RR. CONCLUSIONS: The authors argue that for cohort studies, the use of logistic regression should be sharply curtailed, and that instead, binomial regression be used to directly estimate RRs and associated CIs.
PURPOSE: In cohort studies of common outcomes, odds ratios (ORs) may seriously overestimate the true effect of an exposure on the outcome of interest (as measured by the risk ratio [RR]). Since few study designs require ORs (most frequently, case-control studies), their popularity is due to the widespread use of logistic regression. Because ORs are used to approximate RRs so frequently, methods have been published in the general medical literature describing how to convert ORs to RRs; however, these methods may produce inaccurate confidence intervals (CIs). The authors explore the use of binomial regression as an alternative technique to directly estimate RRs and associated CIs in cohort studies of common outcomes. METHODS: Using actual study data, the authors describe how to perform binomial regression using the SAS System for Windows, a statistical analysis program widely used by US health researchers. RESULTS: In a sample data set, the OR for the exposure of interest overestimated the RR more than twofold. The 95% CIs for the OR and converted RR were wider than for the directly estimated RR. CONCLUSIONS: The authors argue that for cohort studies, the use of logistic regression should be sharply curtailed, and that instead, binomial regression be used to directly estimate RRs and associated CIs.
Authors: Christina M Bancej; Norm Campbell; Donald W McKay; Marianne Nichol; Robin L Walker; Janusz Kaczorowski Journal: Can J Cardiol Date: 2010-05 Impact factor: 5.223
Authors: Maria Aparecida Turci; Maria Fernanda Lima-Costa; Fernando Augusto Proietti; Cibele C Cesar; James Macinko Journal: J Urban Health Date: 2010-12 Impact factor: 3.671
Authors: Anna S Graseck; Gina M Secura; Jenifer E Allsworth; Tessa Madden; Jeffrey F Peipert Journal: Obstet Gynecol Date: 2010-12 Impact factor: 7.661
Authors: Salomeh Keyhani; Joseph S Ross; Paul Hebert; Cornelia Dellenbaugh; Joan D Penrod; Albert L Siu Journal: Am J Public Health Date: 2007-10-30 Impact factor: 9.308
Authors: Robert J Fortuna; Fang Zhang; Dennis Ross-Degnan; Francis X Campion; Jonathan A Finkelstein; Jamie B Kotch; Adrianne C Feldstein; David H Smith; Steven R Simon Journal: J Gen Intern Med Date: 2009-05-28 Impact factor: 5.128
Authors: Neera K Goyal; Eric S Hall; David E Jones; Jareen K Meinzen-Derr; Jodie A Short; Robert T Ammerman; Judith B Van Ginkel Journal: Am J Public Health Date: 2013-12-19 Impact factor: 9.308