Modification of GEE1 and linear mixed-effects models for heteroscedastic longitudinal Gaussian data. Issue 22 (17th November 2017)

• Record Type: Journal Article
• Authors: Nakashima, Eiji
• Is Part Of: Communications in statistics. Volume 46:Issue 22(2017)
• Page Start: 11110
• Page End: 11122
• Publication Date: 2017-11-17
• Subjects: GEE -- GLM -- Linear mixed-effects model -- Least square -- Longitudinal data -- Population averaged model -- Subject-specific model; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2016.1260737
• Languages: English
• ISSNs: 0361-0926

Abstract

ABSTRACT: A characterization of GLMs is given. Modification of the Gaussian GEE1, modified GEE1, was applied to heteroscedastic longitudinal data, to which linear mixed-effects models are usually applied. The modified GEE1 models scale multivariate data to homoscedastic data maintaining the correlation structure and apply usual GEE1 to homoscedastic data, which needs no-diagnostics for diagonal variances. Relationships among multivariate linear regression methods, ordinary/generalized LS, naïve/modified GEE1, and linear mixed-effects models were discussed. An application showed modified GEE1 gave most efficient parameter estimation. Correct specification of the main diagonals of heteroscedastic data variance appears to be more important for efficient mean parameter estimation.