Many of the classical estimation methods of statistics lead to estimators that solve an equation. The likelihood equation, the least squares equation and equations arising in method of moments estimation are all examples of estimating equations. In special cases, estimating equation-based estimators often have appeal because they correspond to the maximum or minimum of an objective function. In such cases, an intuitively reasonable criterion for estimation, such as minimizing the Euclidean distance between the observation vector and the fitted value, motivates the procedure. In general, however, solutions of estimating equations need not minimize an objective function. Therefore, when the assumed model for the data is inaccurate, it is unclear what aspect of the data is being described by an estimating equation-based estimator. Since the landmark article of Liang and Zeger (1986), there has been considerable interest in using estimating equations for longitudinal and other clustered da...

this paper we describe the Hall and Severini approach and compare it with other GEE-related methods for marginal models. It is seen that the proposed estimating equations are closely related to methods that have been proposed for inference in subject-specific models including the generalized linear mixed model and nonlinear mixed model. We also report results of a simulation study in which EGEE is compared with the alternating logistic regressions approach of Carey, Zeger and Diggle (1993) for clustered binary data.

The author describes the relationship between the extended generalized estimating equations (EGEEs) of Hall & Severini (1998) and various similar methods. He proposes a true extended quasi-likelihood approach for the clustered data case and explores restricted maximum likelihood-like versions of the EGEE and extended quasi-likelihood estimating equations. He also presents simulation results comparing the various estimators in terms of mean squared error of estimation based on three moderate sample size, discrete data situations. R ESUM E L'auteur decrit la relation entre les equations d'estimation generalisees etendues (EEGE) de Hall & Severini (1998) et plusieurs methodes similaires. Il propose une veritable approche de quasi-vraisemblance etendue adaptee au cas de donnees regroupees et etudie des versions de type maximum de vraisemblance restreint des EEGE et des equations d'estimation de quasi-vraisemblance. Il presente de plus des resultats de simulation comparant les di#erents...