Analysis of Incomplete Multivariate Data

ISBN-13: 9780412040610 / Angielski / Twarda / 1997 / 444 str.

J. L. Schafer

Opis

This book presents a unified, Bayesian approach to the analysis of inc omplete multivariate data, covering datasets in which the variables ar e continuous, categorical, or both. It is written for applied statisti cians, biostatisticians, practitioners of sample surveys, graduate stu dents, and other methodologically-orientated researchers in search of practical tools to handle missing data. The focus is applied where ne cessary to help readers thoroughly understand the statistical properti es of those methods, and the behavior of the accompanying algorithms. All techniques are illustrated with real data examples, with extended discussion and practical advice. All of the algorithms described in t his book have been implemented by the author for general use in the st atistical languages S and S Plus.

Recenzje

"Overall, the book provides a sound basis on which one can build when dealing with real data…I take pleasure in recommending this well-written text."
-Rainer Schlittgen in Statistical Papers
"This book provides an excellent introduction to statistical inference…Thanks to the clear and relatively complete treatment of many of the main ideas in this area, even theoretically oriented readers may find this book worthwhile."
-Mark Steel, Mathematical Reviews

Spis treści

Introduction Assumptions EM and Inference by Data Augmentation Methods for Normal Data More on the Normal Model Methods for Categorical Data Loglinear Models Methods for Mixed Data Further Topics Appendices References Index

O autorze

J.L. Schafer