Paper Info
Title
Optimal model averaging estimation for correlation structure in generalized estimating equations
Abstract
Longitudinal data analysis requires a proper estimation of the within-cluster correlation structure in order to achieve efficient estimates of the regression parameters. When applying likelihood-based methods one may select an optimal correlation structure by the AIC or BIC. However, such information criteria are not applicable for estimating equation based approaches. In this paper we develop a model averaging approach to estimate the correlation matrix by a weighted sum of a group of patterned correlation matrices under the GEE framework. The optimal weight is determined by minimizing the difference between the weighted sum and a consistent yet inefficient estimator of the correlation structure. The computation of our proposed approach only involves a standard quadratic programming on top of the standard GEE procedure and can be easily implemented in practice. We provide theoretical justifications and extensive numerical simulations to support the application of the proposed estimator. A couple of well-known longitudinal data sets are revisited where we implement and illustrate our methodology.
Year
DOI
Venue
2019
10.1080/03610918.2017.1419260
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
Keywords
Field
DocType
Asymptotical optimality,Efficient estimation,Generalized estimating equation,Longitudinal data,Misspecification,Model averaging,Working correlation
Applied mathematics,Information Criteria,Matrix (mathematics),Quadratic programming,Covariance matrix,Statistics,Generalized estimating equation,Mathematics,Estimating equations,Estimator,Computation
Journal
Volume
Issue
ISSN
48.0
5.0
0361-0918
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Fang Fang101.01
J. Li282.05
Jingli Wang311.69