»  Home »  Bookstore »  Title index »  Categorical, count, and censored outcomes »  Ordered Regression Models: Parallel, Partial, and Non-Parallel Alternatives

Ordered Regression Models: Parallel, Partial, and Non-Parallel Alternatives

Click to enlarge
See the back cover

What are VitalSource eBooks?
Your access code will be emailed upon purchase.

eBook not available for this title

eBook not available for this title

 Authors: Andrew S. Fullerton and Jun Xu Publisher: CRC Press Copyright: 2016 ISBN-13: 978-1-4665-6973-7 Pages: 171; hardcover
 Authors: Andrew S. Fullerton and Jun Xu Publisher: CRC Press Copyright: 2016 ISBN-13: Pages: 171; eBook Price: $0.00  Authors: Andrew S. Fullerton and Jun Xu Publisher: CRC Press Copyright: 2016 ISBN-13: Pages: 171; Kindle Price:$

Comment from the Stata technical group

In Ordered Regression Models: Parallel, Partial, and Non-Parallel Alternatives, Fullerton and Xu provide a thorough treatment of models for ordinal data. This book will appeal to researchers from any discipline who wish to build on their knowledge of linear, logistic, and probit regression and learn both theoretical and practical concepts related to a variety of models for ordinal outcomes.

As the title indicates, the models presented are partitioned into three groups based on whether a parallel regression assumption is made for all covariates, for a subset of the covariates, or for none of the covariates. Under each of these assumptions, the authors describe three models—cumulative, continuation ratio, and adjacent category—from which a researcher can choose, depending on the probability of interest. They also include worked examples with real data and provide advice regarding interpretation, presentation of results, choice of model, and common problems that arise. Example Stata commands for fitting these models are shown at the end of the chapters.