Goldstein H. Multilevel Statistical Models

Wiley, 2010. — 384 p. — 4th Ed. — ISBN: 0470748656, 9780470748657.
Throughout the social, medical and other sciences the importance of understanding complex hierarchical data structures is well understood. Multilevel modelling is now the accepted statistical technique for handling such data and is widely available in computer software packages. A thorough understanding of these techniques is therefore important for all those working in these areas. This new edition of Multilevel Statistical Models brings these techniques together, starting from basic ideas and illustrating how more complex models are derived. Bayesian methodology using MCMC has been extended along with new material on smoothing models, multivariate responses, missing data, latent normal transformations for discrete responses, structural equation modeling and survival models.Key FeaturesProvides a clear introduction and a comprehensive account of the of multilevel models.
New methodological developments and applications are explored.
Written by a leading expert in the field of multilevel methodology.
Illustrated throughout with real-life examples, explaining theoretical concepts.
This book is suitable as a comprehensive text for postgraduate courses, as well as a general reference guide. Applied statisticians in the social sciences, economics, biological and medical disciplines will find this book beneficial.Dedication.Acknowledgements.
Notation.
A general classification notation and diagram.An introduction to multilevel models.
The 2-level model.
Three level models and more complex hierarchical structures.
Multilevel Models for discrete response data.
Models for repeated measures data.
Multivariate multilevel data.
Latent normal models for multivariate data.
Multilevel factor analysis, structural equation and mixture models.
Nonlinear multilevel models.
Multilevel modelling in sample surveys.
Multilevel event history and survival models.
Cross classified data structures.
Multiple membership models.
Measurement errors in multilevel models.
Smoothing models for multilevel data.
Missing data, partially observed data and multiple imputation.
Multilevel models with correlated random effects.
Software for multilevel modelling.Author index.
Subject index.