A prediction criterion for working correlation structure selection in GEE

Abstract: Generalized estimating equations (GEE) is one of the most commonly used methods for marginal regression analysis of longitudinal data, especially with discrete outcomes. The GEE method models the association among the responses of a subject through a working correlation matrix and correct specification of the working correlation structure ensures efficient estimation of the regression parameters. This study proposes a predicted residual sum of squares (PRESS) statistic as a working correlation selection criterion in GEE. An extensive simulation study is designed to assess the performance of the proposed GEE PRESS criterion and to compare its performance with well-known existing criteria in the literature. The results show that the GEE PRESS criterion has better performance than the weighted error sum of squares SC criterion in all cases and is comparable with that of other existing criteria when the true working correlation structure is AR(1) or exchangeable. Lastly, the working correlation selection criteria are illustrated with the Coronary Artery Risk Development in Young Adults study.