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.
Introduction to Agreement Introduction 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 Introduction 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 Consensus More Than Two Raters Introduction 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 Introduction 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 Introduction Nominal Responses Ordinal Responses More than Two Raters Other Methods for Patterns of Agreement Summary of Modeling and Agreement Agreement with Quantitative Scores Introduction Regression and Correlation The Analysis of Variance Intraclass Correlation Coefficient for Agreement With Covariates Other Considerations with Continuous Scores Sample Sizes for Agreement Studies Introduction 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 Introduction Bayes Theorem Prior Information Posterior Information Inference Predictive Inference Checking Model Assumptions Sample Size Problems Computing Appendix B: Introduction to WinBUGS Introduction Download The Essentials Execution Output Examples Summary Exercises appear at the end of each chapter.