David B Richardson1, Alan C Kinlaw2, Richard F MacLehose3, Stephen R Cole2. 1. Department of Epidemiology, School of Public Health, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA and david.richardson@unc.edu. 2. Department of Epidemiology, School of Public Health, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA and. 3. Division of Epidemiology and Community Health, School of Public Health, University of Minnesota, Minneapolis, MN, USA.
Abstract
BACKGROUND: Epidemiologists often analyse binary outcomes in cohort and cross-sectional studies using multivariable logistic regression models, yielding estimates of adjusted odds ratios. It is widely known that the odds ratio closely approximates the risk or prevalence ratio when the outcome is rare, and it does not do so when the outcome is common. Consequently, investigators may decide to directly estimate the risk or prevalence ratio using a log binomial regression model. METHODS: We describe the use of a marginal structural binomial regression model to estimate standardized risk or prevalence ratios and differences. We illustrate the proposed approach using data from a cohort study of coronary heart disease status in Evans County, Georgia, USA. RESULTS: The approach reduces problems with model convergence typical of log binomial regression by shifting all explanatory variables except the exposures of primary interest from the linear predictor of the outcome regression model to a model for the standardization weights. The approach also facilitates evaluation of departures from additivity in the joint effects of two exposures. CONCLUSIONS: Epidemiologists should consider reporting standardized risk or prevalence ratios and differences in cohort and cross-sectional studies. These are readily-obtained using the SAS, Stata and R statistical software packages. The proposed approach estimates the exposure effect in the total population.
BACKGROUND: Epidemiologists often analyse binary outcomes in cohort and cross-sectional studies using multivariable logistic regression models, yielding estimates of adjusted odds ratios. It is widely known that the odds ratio closely approximates the risk or prevalence ratio when the outcome is rare, and it does not do so when the outcome is common. Consequently, investigators may decide to directly estimate the risk or prevalence ratio using a log binomial regression model. METHODS: We describe the use of a marginal structural binomial regression model to estimate standardized risk or prevalence ratios and differences. We illustrate the proposed approach using data from a cohort study of coronary heart disease status in Evans County, Georgia, USA. RESULTS: The approach reduces problems with model convergence typical of log binomial regression by shifting all explanatory variables except the exposures of primary interest from the linear predictor of the outcome regression model to a model for the standardization weights. The approach also facilitates evaluation of departures from additivity in the joint effects of two exposures. CONCLUSIONS: Epidemiologists should consider reporting standardized risk or prevalence ratios and differences in cohort and cross-sectional studies. These are readily-obtained using the SAS, Stata and R statistical software packages. The proposed approach estimates the exposure effect in the total population.
Authors: Aaron P Mitchell; Alan C Kinlaw; Sharon Peacock-Hinton; Stacie B Dusetzina; Hanna K Sanoff; Jennifer L Lund Journal: Oncologist Date: 2019-10-14
Authors: Mark J D Jordans; Nagendra P Luitel; Emily Garman; Brandon A Kohrt; Sujit D Rathod; Pragya Shrestha; Ivan H Komproe; Crick Lund; Vikram Patel Journal: Br J Psychiatry Date: 2019-01-25 Impact factor: 9.319
Authors: Linda S Ng; Jack M Guralnik; Cora Man; Carolyn DiGuiseppi; David Strogatz; David W Eby; Lindsay H Ryan; Lisa J Molnar; Marian E Betz; Linda Hill; Guohua Li; Christopher L Crowe; Thelma J Mielenz Journal: Gerontologist Date: 2020-01-24
Authors: Godwin Anguzu; Andrew Flynn; Joseph Musaazi; Ronnie Kasirye; Leonard K Atuhaire; Agnes N Kiragga; Allen Kabagenyi; Andrew Mujugira Journal: Int J STD AIDS Date: 2018-11-11 Impact factor: 1.359
Authors: David B Richardson; Alexander P Keil; Jessie K Edwards; Alan C Kinlaw; Stephen R Cole Journal: Am J Epidemiol Date: 2020-10-01 Impact factor: 4.897
Authors: Alan C Kinlaw; Michele Jonsson Funk; Mitchell M Conover; Virginia Pate; Alayne D Markland; Jennifer M Wu Journal: Med Care Date: 2018-02 Impact factor: 2.983
Authors: Lisa M Pollack; Margaret A Olsen; Sarah J Gehlert; Su-Hsin Chang; Jerry L Lowder Journal: J Minim Invasive Gynecol Date: 2019-09-10 Impact factor: 4.137
Authors: Stephen R Cole; Jessie K Edwards; Daniel Westreich; Catherine R Lesko; Bryan Lau; Michael J Mugavero; W Christopher Mathews; Joseph J Eron; Sander Greenland Journal: Biom J Date: 2017-10-27 Impact factor: 2.207