Loading...

Analysis of Ordinal Categorical Data, 2nd Edition

ISBN: 978-0-470-59399-8

July 2012

424 pages

Description
Praise for the First Edition:

"The author has a fluent, easy-to-read style, and well-chosen interesting material to present and illustrate the ideas to the newcomer and the old hand alike."
Journal of the Royal Statistical Society

Categorical data having ordered categories are common in practice, especially in applications throughout the biomedical and social sciences. Thoroughly updated to reflect developments since the publication of its predecessor, Analysis of Ordinal Categorical Data, Second Edition presents a comprehensive survey of methods for analyzing ordinal categorical data, complete with coverage of the most recent research.

The author highlights various modeling techniques, including cumulative logit models with and without proportional odds structure, adjacent-categories logit and continuation-ratio logit models, stereotype models, association models for ordinal odds ratios, and models for clustered ordinal data. Additional features of this Second Edition include:

  • A new chapter on marginal models for multivariate ordinal responses, using maximum likelihood and generalized estimating equations for model fitting

  • A new chapter on random effects models for clustered ordinal data

  • A new chapter on Bayesian approaches for analyzing ordinal data

  • Models and order-restricted inference methods for various types of ordinal odds ratios, including local odds ratios, cumulative odds ratios, and global odds ratios

  • Presentation of non-model-based methods, such as nonparametric rank methods that also apply to ordered categorical data

Each chapter concludes with notes on relevant research literature as well as exercises that allow readers to test their comprehension of the presented concepts. A detailed appendix discusses the use of the latest software such as SAS, R, SPSS, and Stata, and the book's related Web site provides further instructions for the use of these software packages along with complete data sets.

Analysis of Ordinal Categorical Data, Second Edition is an excellent book for courses on categorical data analysis at the upper-undergraduate and graduate levels. It is also an invaluable resource for researchers and practitioners who conduct data analysis in the areas of public health, business, medicine, and the social and behavioral sciences.

About the Author
ALAN AGRESTI, PhD, is Distinguished Professor Emeritus in the Department of Statistics at the University of Florida and Visiting Professor in the Department of Statistics at Harvard University. A Fellow of the American Statistical Association and the Institute of Mathematical Statistics, Dr. Agresti has published extensively on the topic of categorical data analysis and has presented lectures and short courses on the subject in more than thirty countries. He is the author of Categorical Data Analysis, Second Edition and An Introduction to Categorical Data Analysis, Second Edition, both published by Wiley.
New to Edition
  • Now with a revised structure, the more advanced material can be found in the ends of chapters
  • Coverage has been updated to feature recent methods such as log linear, logit, and multinomial logistic regression; repeated measurement ordinal data; and clustering.
  • Section notes have been added to provide reference to further details and to recent relevant research.
  • All of the exercises have been changed, updated, and streamlined. They now require data analyses and deal with interpretations of the methods.
  • A related Web site features data sets, SAS programs, and additional supplemental material.
Features
  • This is the first book of its kind to deal comprehensively with specialized methods for categorical data with ordered categories, though now the more advanced material is relegated to the ends of chapters.
  • Coverage has been updated to feaature recent methods such as log linear, logit, and multinomial logistic regression; repeated measurement ordinal data; and clustering.
  • Section notes have been added to provide reference to further details and to recent relevant research.
  • The use of existing statistical computer packages for implementing the methods is explained; these include SAS, SPSS, GLIM and R subroutines.
  • All of the exercises have been changed, updated, and streamlined. They now require data analyses and deal with interpretations of the methods.
  • An extensive bibliography includes articles dealing with the analysis of ordinal categorical data, pulling together research in the last two decades from widely divergent sources.
  • A related Web site features data sets, SAS programs, and additional supplemental material.