Lawrence C Kleinman1, Edward C Norton. 1. Department of Health Policy, Mount Sinai School of Medicine, Box 1077, New York, NY 10029, USA. lawrence.kleinman@mssm.edu
Abstract
OBJECTIVE: To develop and validate a general method (called regression risk analysis) to estimate adjusted risk measures from logistic and other nonlinear multiple regression models. We show how to estimate standard errors for these estimates. These measures could supplant various approximations (e.g., adjusted odds ratio [AOR]) that may diverge, especially when outcomes are common. STUDY DESIGN: Regression risk analysis estimates were compared with internal standards as well as with Mantel-Haenszel estimates, Poisson and log-binomial regressions, and a widely used (but flawed) equation to calculate adjusted risk ratios (ARR) from AOR. DATA COLLECTION: Data sets produced using Monte Carlo simulations. PRINCIPAL FINDINGS: Regression risk analysis accurately estimates ARR and differences directly from multiple regression models, even when confounders are continuous, distributions are skewed, outcomes are common, and effect size is large. It is statistically sound and intuitive, and has properties favoring it over other methods in many cases. CONCLUSIONS: Regression risk analysis should be the new standard for presenting findings from multiple regression analysis of dichotomous outcomes for cross-sectional, cohort, and population-based case-control studies, particularly when outcomes are common or effect size is large.
OBJECTIVE: To develop and validate a general method (called regression risk analysis) to estimate adjusted risk measures from logistic and other nonlinear multiple regression models. We show how to estimate standard errors for these estimates. These measures could supplant various approximations (e.g., adjusted odds ratio [AOR]) that may diverge, especially when outcomes are common. STUDY DESIGN: Regression risk analysis estimates were compared with internal standards as well as with Mantel-Haenszel estimates, Poisson and log-binomial regressions, and a widely used (but flawed) equation to calculate adjusted risk ratios (ARR) from AOR. DATA COLLECTION: Data sets produced using Monte Carlo simulations. PRINCIPAL FINDINGS: Regression risk analysis accurately estimates ARR and differences directly from multiple regression models, even when confounders are continuous, distributions are skewed, outcomes are common, and effect size is large. It is statistically sound and intuitive, and has properties favoring it over other methods in many cases. CONCLUSIONS: Regression risk analysis should be the new standard for presenting findings from multiple regression analysis of dichotomous outcomes for cross-sectional, cohort, and population-based case-control studies, particularly when outcomes are common or effect size is large.
Authors: Michele L Allen; Marc N Elliott; Leo S Morales; Allison L Diamant; Katrin Hambarsoomian; Mark A Schuster Journal: Am J Public Health Date: 2006-11-30 Impact factor: 9.308
Authors: Eric M Cheng; Salomeh Keyhani; Susan Ofner; Linda S Williams; Paul L Hebert; Diana L Ordin; Dawn M Bravata Journal: Neurology Date: 2012-06-13 Impact factor: 9.910
Authors: Allison Kempe; Laura P Hurley; Cristina V Cardemil; Mandy A Allison; Lori A Crane; Michaela Brtnikova; Brenda L Beaty; Laura J Pabst; Megan C Lindley Journal: Am J Prev Med Date: 2016-09-14 Impact factor: 5.043
Authors: Alene Kennedy-Hendricks; Andrew J Epstein; Elizabeth A Stuart; Rebecca L Haffajee; Emma E McGinty; Alisa B Busch; Haiden A Huskamp; Colleen L Barry Journal: Pediatrics Date: 2018-08 Impact factor: 7.124
Authors: Paul N Fiorilli; Karl E Minges; Jeph Herrin; John C Messenger; Henry H Ting; Brahmajee K Nallamothu; Rebecca S Lipner; Brian J Hess; Eric S Holmboe; Joseph J Brennan; Jeptha P Curtis Journal: Circulation Date: 2015-09-18 Impact factor: 29.690
Authors: Emily C Williams; Anna D Rubinsky; Laura J Chavez; Gwen T Lapham; Stacey E Rittmueller; Carol E Achtmeyer; Katharine A Bradley Journal: Addiction Date: 2014-06-12 Impact factor: 6.526