On the use of between–within models to adjust for confounding due to unmeasured cluster-level covariates. Issue 5 (28th May 2017)

• Record Type: Journal Article
• Authors: Brumback, Babette A.; Li, Li; Cai, Zhuangyu
• Is Part Of: Communications in statistics. Volume 46:Issue 5(2017)
• Page Start: 3841
• Page End: 3854
• Publication Date: 2017-05-28
• Subjects: Clustered data -- Generalized linear mixed models -- Heteroscedasticity -- Unmeasured confounding; 62-07; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2015.1024858
• Languages: English
• ISSNs: 0361-0918

Abstract

ABSTRACT: Between–within models are generalized linear mixed models (GLMMs) for clustered data that incorporate a random intercept together with fixed effects for within-cluster and between-cluster covariates; the between-cluster covariates represent the cluster means of the within-cluster covariates. One popular use of these models is to adjust for confounding of the effect of within-cluster covariates due to unmeasured between-cluster covariates. Previous research has shown via simulations that using this approach can yield inconsistent estimators. We present theory and simulations as evidence that a primary cause of the inconsistency is heteroscedasticity of the linearized version of the GLMM used for estimation.