Models for discrete longitudinal data /
Molenberghs, Geert.
Models for discrete longitudinal data / Geert Molenberghs, Geert Verbeke. - New York ; London : Springer, c2006. - xxii, 683 p. : ill. 25 cm. - Springer series in statistics. . - Springer series in statistics. .
Includes bibliographical references and index.
Introduction --
Motivating studies --
Generalized linear models --
Linear mixed models for Gaussian longitudinal data --
Model families --
The strength of marginal models --
Likelihood-based marginal models --
Generalized estimating equations --
Pseudo-likelihood --
Fitting marginal models with SAS --
Conditional models --
Pseudo-likehood --
From subject-specific to random-effects models --
The generalized linear mixed model (GLMM) --
Fitting generalized linear mixed models with SAS --
Marginal versus random-effects models The analgesic trial --
Ordinal data --
The epilepsy data --
Non-linear models --
Pseudo-likelihood for a hierarchical model --
Random-effects models with serial correlation --
Non-Gaussian random effects --
Joint continuous and discrete responses --
High-dimensional joint models --
Missing data concepts --
Simple methods, direct likelihood, and WGEE --
Multiple imputation and the EM algorithm --
Selection models --
Pattern-mixture models --
Sensitivity analysis --
Incomplete data and SAS. TOC
Summary:
The linear mixed model is the main parametric tool for the analysis of continuous longitudinal data. This book shows how the different approaches can be implemented within the SAS software package.
0387251448 (hbk.) 9780387251448
2005923258
Multivariate analysis.
Longitudinal method.
QA278 / .M65 2005
519.53 / MOM 2006
Models for discrete longitudinal data / Geert Molenberghs, Geert Verbeke. - New York ; London : Springer, c2006. - xxii, 683 p. : ill. 25 cm. - Springer series in statistics. . - Springer series in statistics. .
Includes bibliographical references and index.
Introduction --
Motivating studies --
Generalized linear models --
Linear mixed models for Gaussian longitudinal data --
Model families --
The strength of marginal models --
Likelihood-based marginal models --
Generalized estimating equations --
Pseudo-likelihood --
Fitting marginal models with SAS --
Conditional models --
Pseudo-likehood --
From subject-specific to random-effects models --
The generalized linear mixed model (GLMM) --
Fitting generalized linear mixed models with SAS --
Marginal versus random-effects models The analgesic trial --
Ordinal data --
The epilepsy data --
Non-linear models --
Pseudo-likelihood for a hierarchical model --
Random-effects models with serial correlation --
Non-Gaussian random effects --
Joint continuous and discrete responses --
High-dimensional joint models --
Missing data concepts --
Simple methods, direct likelihood, and WGEE --
Multiple imputation and the EM algorithm --
Selection models --
Pattern-mixture models --
Sensitivity analysis --
Incomplete data and SAS. TOC
Summary:
The linear mixed model is the main parametric tool for the analysis of continuous longitudinal data. This book shows how the different approaches can be implemented within the SAS software package.
0387251448 (hbk.) 9780387251448
2005923258
Multivariate analysis.
Longitudinal method.
QA278 / .M65 2005
519.53 / MOM 2006