A note on marginalization of regression parameters from mixed models of binary outcomes. Issue 1 (20th April 2017)

• Record Type: Journal Article
• Authors: Hedeker, Donald; du Toit, Stephen H. C.; Demirtas, Hakan; Gibbons, Robert D.
• Is Part Of: Biometrics. Volume 74:Issue 1(2018)
• Page Start: 354
• Page End: 361
• Publication Date: 2017-04-20
• Subjects: Clustered data -- Longitudinal data -- Multilevel models -- Population‐averaged estimates -- Subject‐specific estimates; Biometry -- Periodicals; 570.15195
• DOI: 10.1111/biom.12707
• Languages: English
• ISSNs: 0006-341X

Abstract

Summary: This article discusses marginalization of the regression parameters in mixed models for correlated binary outcomes. As is well known, the regression parameters in such models have the "subject‐specific" (SS) or conditional interpretation, in contrast to the "population‐averaged" (PA) or marginal estimates that represent the unconditional covariate effects. We describe an approach using numerical quadrature to obtain PA estimates from their SS counterparts in models with multiple random effects. Standard errors for the PA estimates are derived using the delta method. We illustrate our proposed method using data from a smoking cessation study in which a binary outcome (smoking, Y/N) was measured longitudinally. We compare our estimates to those obtained using GEE and marginalized multilevel models, and present results from a simulation study.