Extended Generalized Estimating Equations for Clustered Data
针对聚类数据中组内相关性的处理难题，提出一种扩展广义估计方程方法，可同时估计回归和关联参数，且回归估计量在相关性模型错误设定下仍保持一致性。
Abstract Typically, analysis of data consisting of multiple observations on a cluster is complicated by within-cluster correlation. Estimating equations for generalized linear modeling of clustered data have recently received much attention. This article proposes an extension to the generalized estimating equation method proposed by Liang and Zeger, which treats within-cluster correlations as nuisance parameters. Using ideas from extended quasi-likelihood, estimating equations for regression and association parameters are provided simultaneously. The resulting estimators are proven to be asymptotically normal and consistent under certain conditions. The consistency of regression estimators allows incorrect modeling of the correlation among repeated responses. The method is illustrated with an analysis of data from a developmental toxicity study.