Broemeling Bayesian Methods for Measures of Agreement

1. Auflage 2009
ISBN: 978-1-4200-8343-9
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 340 Seiten

Reihe: Chapman & Hall/CRC Biostatistics Series

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.

Autoren/Hrsg.

Broemeling, Lyle D.

Fachgebiete

• Mathematik | Informatik Mathematik Stochastik Wahrscheinlichkeitsrechnung
• Mathematik | Informatik Mathematik Stochastik Mathematische Statistik

Inhaltsverzeichnis

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.