Correlated Data Analysis: Modeling, Analytics, and Applications

and Examples.- Dispersion Models.- Inference Functions.- Modeling Correlated Data.- Marginal Generalized Linear Models.- Vector Generalized Linear Models.- Mixed-Effects Models: Likelihood-Based Inference.- Mixed-Effects Models: Bayesian Inference.- Linear Predictors.- Generalized State Space Models.- Generalized State Space Models for Longitudinal Binomial Data.- Generalized State Space Models for Longitudinal Count Data.- Missing Data in Longitudinal Studies.

Aimed at graduate students and researchers, this book deals with recent developments in correlated data analysis. It uses the class of dispersion models as marginal components in the formulation of joint models for correlated data. This enables the book to cover a broader range of data types than the traditional generalized linear models, such as correlated directional data and correlated compositional data. The reader is provided with a systematic treatment for the topic of estimating functions, and both generalized estimating equations (GEE) and quadratic inference functions (QIF) are studied as special cases. In addition to the discussions on marginal models and mixed-effects models, this book covers new topics on joint regression analysis based on Gaussian copulas and state space models for longitudinal data from long time series. Various real-world data examples, numerical illustrations and software usage tips are included too. Applied statisticians and data analysts in many subject-matter fields will find this text essential.

From the reviews:

"The book presents recent developments in the field of correlated data analysis. Its aim is to give a systematic account of regression models and their application to the modelling and analysis of correlated data. ... Various real-world data examples, numerical illustrations and software usage tips are presented throughout the book, making it suitable for graduate courses on correlated data analysis. ... also serve as a reference for those that need theoretical explanations and a deeper understanding of the theory that underlies the related analyses." (Christina Diakaki, Zentralblatt MATH, Vol. 1132 (10), 2008)

"This is an ambitious book that covers an enormous amount of material in a relatively small number of pages. ... would be a good addition to the library of a statistician interested in both the theoretical and applied aspects of correlated data analysis. ... it would be a good choice for a graduate-level course focusing on the theoretical aspects of longitudinal and discrete time series data analysis. It also might serve as a good reference book for a more applied course on this subject." (Paul S. Albert, Journal of the American Statistical Association, Vol. 103 (484), December, 2008)

"This book is a highly recommended text for those armed with a strong computational background and ambitious enough to attack real world problems of high dimension, unknown complexity, and at most hazy knowledge of the causalities. Such problems abound. i:.g., in medicine, biology, meteorology, and climate change.... The results as presented are impressive. It is amazing what can be done if one uses available software. e.g., from SAS at several instances or of related software sources, e.g., WINBUGS or "R." Anyone doing similar empirical work should read this book. (Götz Ube, AStA - Advances in Statistical Analysis. DOI 10.1007/s10182-008-9)

"This book focuses on correlated data analysis and is divided into three main