Bayesian Methods for Measures of Agreement  book cover
1st Edition

Bayesian Methods for Measures of Agreement

ISBN 9781420083415
Published January 12, 2009 by Chapman and Hall/CRC
340 Pages - 28 B/W Illustrations

SAVE ~ $25.00
was $125.00
USD $100.00

Prices & shipping based on shipping country


Book Description

Using WinBUGS to implement Bayesian inferences of estimation and testing hypotheses, Bayesian Methods for Measures of Agreement presents useful methods for the design and analysis of agreement studies. It focuses on agreement among the various players in the diagnostic process.

The author employs a Bayesian approach to provide statistical inferences based on various models of intra- and interrater agreement. He presents many examples that illustrate the Bayesian mode of reasoning and explains elements of a Bayesian application, including prior information, experimental information, the likelihood function, posterior distribution, and predictive distribution. The appendices provide the necessary theoretical foundation to understand Bayesian methods as well as introduce the fundamentals of programming and executing the WinBUGS software.

Taking a Bayesian approach to inference, this hands-on book explores numerous measures of agreement, including the Kappa coefficient, the G coefficient, and intraclass correlation. With examples throughout and end-of-chapter exercises, it discusses how to successfully design and analyze an agreement study.

Table of Contents

Introduction to Agreement


Agreement and Statistics

The Bayesian Approach

Some Examples of Agreement

Sources of Information

Software and Computing

A Preview of the Book

Bayesian Methods of Agreement for Two Raters


The Design of Agreement Studies

Precursors of Kappa

Chance Corrected Measures of Agreement

Conditional Kappa

Kappa and Stratification

Weighted Kappa

Intraclass Kappa

Other Measures of Agreement

Agreement with a Gold Standard

Kappa and Association


More Than Two Raters


Kappa with Many Raters

Partial Agreement

Stratified Kappa

Intraclass Kappa

The Fleiss Generalized Kappa

The G Coefficient and Other Indices

Kappa and Homogeneity

Introduction to Model-Based Approaches

Agreement and Matching

Agreement and Correlated Observations


An Example of Paired Observations

The Oden Pooled Kappa and Schouten Weighted Kappa

A Generalized Correlation Model

The G Coefficient and Other Indices of Agreement

Homogeneity with Dependent Data

Logistic Regression and Agreement

Modeling Patterns of Agreement


Nominal Responses

Ordinal Responses

More than Two Raters

Other Methods for Patterns of Agreement

Summary of Modeling and Agreement

Agreement with Quantitative Scores


Regression and Correlation

The Analysis of Variance

Intraclass Correlation Coefficient for Agreement

With Covariates

Other Considerations with Continuous Scores

Sample Sizes for Agreement Studies


The Classical and Bayesian Approaches to Power Analysis

The Standard Populations: Classical and Bayesian Approaches

Kappa, the G Coefficient, and Other Indices

The Logistic Linear Model

Regression and Correlation

The Intraclass Correlation

Bayesian Approaches to Sample Size

Appendix A: Bayesian Statistics


Bayes Theorem

Prior Information

Posterior Information


Predictive Inference

Checking Model Assumptions

Sample Size Problems


Appendix B: Introduction to WinBUGS



The Essentials





Exercises appear at the end of each chapter.

View More



Lyle D. Broemeling


"This book is a welcome addition to the literature on Bayesian inference as it presents methods for the design and analysis of agreement studies. … The approach presented by the author is novel and the novice will find a helpful introduction to Bayesian inference in an appendix. … The text is readable and will form a valuable reference source. For those unfamiliar with WinBUGS, the author introduces the fundamentals of programming and executing BUGS."
International Statistical Review, 2010

"This book deals with measures of agreement from a Bayesian perspective, focusing mainly on variants of Cohen’s κ, but also other measures included in Shoukri (2003) and von Eye and Mun (2005), frequentist texts for which this book is intended to be a Bayesian companion. Dr. Broemeling uses examples throughout the book to illustrate concepts rather than resorting to jargon … This book would be valuable for those using the methods in Shoukri and von Eye and Mun. …"
Journal of the Royal Statistical Society, Series A, Volume 173, Issue 1, January 2010