Review of Generalized Estimating Equations by Hardin and Hilbe
MetadataShow full item record
Hardin and Hilbe (2003) have written a very detailed book on the statistical methodology of generalized estimating equations (GEE). This work is very much a continuation of their previous book (Hardin and Hilbe 2001), which focused on generalized linear models (GLM): for a review in this journal, see Newson (2001). GEE is an extension to GLM that does not require independent observations and thus can be used to analyze clustered and longitudinal data. At the simplest level, a variance–covariance matrix, which describes the correlation between observations, is specified, and multivariate weighted least squares is used to estimate a GEE model. The book primarily focuses on explaining this process in detail. It assumes that the reader has a fundamental understanding of GLM, maximum likelihood estimation, and distributional statistics. As Hardin and Hilbe are the original authors of the glm and xtgee commands in Stata, which are used to estimate GLM and GEE models, respectively (Hilbe 1993), Stata is often used in the book to present various illustrative examples. The authors also provide detailed information on estimating these models in SAS, S-Plus, and SUDAAN.
Showing items related by title, author, creator and subject.
Baum, CF; Schaffer, ME; Stillman, S (STATA PRESS, 2007)We extend our 2003 paper on instrumental variables and generalized method of moments estimation, and we test and describe enhanced routines that address heteroskedasticity- and autocorrelation-consistent standard errors, ...
On a discrete generalized kinetic approach for modelling persuaders influence in opinion formation processes Bertotti, ML; Delitala, M (Elsevier, 2008)This paper deals with the definition of a general framework, inspired by the discrete generalized kinetic theory, suitable for the description of the evolution of opinions within a population in the presence of some external ...
Baader, F; Borgwardt, S; Penaloza, R (Springer Verlag (Germany), 2015)The combination of Fuzzy Logics and Description Logics (DLs) has been investigated for at least two decades because such fuzzy DLs can be used to formalize imprecise concepts. In particular, tableau algorithms for crisp ...