Main description:

This book will present a unified and up-to date introduction to ROC methodologies, covering both diagnosis (classification) and prediction. The book will emphasize the practical implementation of these methods using standard statistical software such as R and STATA. Existing books tend to be specialized and/or focus on the theoretical derivations, with limited discussion of the use of the concepts and methods across diverse scientific fields and modest emphasis on the implementation of the methods. This book comes after more than a decade of intensive growth in both the methods and the applications of ROC analysis. It is time for a new synthesis. This book will provide a contemporary, integrated exposition of ROC methodology for both classification and prediction, and will include material on multiple class ROC. It will avoid lengthy technical exposition and will provide code and datasets in each chapter. Receiver Operating Characteristic Analysis for Classification and Prediction is primarily for researchers, but will also be useful for those that use ROC analysis in disciplines such as diagnostic medicine, bioinformatics, medical physics, and perception psychology.

Key Features:

Description of basic ROC methodology

R and STATA code

Example Datasets

Not too technical
Many topics not included in other books

Contents:

1. Introduction 2. Measures of Diagnostic and Predictive Performance 3. Statistical inference for the ROC curve 4. Comparing ROC curves 5. The ROC surface and k-class classification for k > 2 6. ROC regression 7. Missing data and errors-in-variables in ROC analysis