Generalized Estimating Equations (Lecture Notes in Statistics Book 204)

Generalized estimating equations have become increasingly popular in biometrical, econometrical, and psychometrical applications because they overcome the classical assumptions of statistics, i.e. independence and normality, which are too restrictive for many problems. Therefore, the main goal of this book is to give a systematic presentation of the original generalized estimating equations (GEE) and some of its further developments. Subsequently, the emphasis is put on the unification of various GEE approaches. This is done by the use of two different estimation techniques, the pseudo maximum likelihood (PML) method and the generalized method of moments (GMM). The author details the statistical foundation of the GEE approach using more general estimation techniques. The book could therefore be used as basis for a course to graduate students in statistics, biostatistics, or econometrics, and will be useful to practitioners in the same fields. Front Matter....Pages i-xv The linear exponential family....Pages 1-10 The quadratic exponential family....Pages 11-20 Generalized linear models....Pages 21-28 Maximum likelihood method....Pages 29-49 Pseudo maximum likelihood method based on the linear exponential family....Pages 51-77 Quasi generalized pseudo maximum likelihood method based on the linear exponential family....Pages 79-99 Pseudo maximum likelihood estimation based on the quadratic exponential family....Pages 101-117 Generalized method of moment estimation....Pages 119-131 Back Matter....Pages 133-144