ROC Curves for Continuous Data

ROC Curves for Continuous Data is the first book dedicated to the analysis of ROC curves, covering the theory, estimation, statistical tests, covariates, comparison of ROC curves, Bayesian methods, and extensions to complex situations. With nearly 5,000 articles published on ROC analysis, the book will guide present and future users of ROC analysis.

Format: Paperback / softback
Length: 256 pages
Publication date: 21 January 2023
Publisher: Taylor & Francis Ltd

Since the widespread adoption of ROC curves across diverse application domains, significant advancements have been scattered across various articles and texts. To address this fragmentation, ROC Curves for Continuous Data emerges as the first dedicated book on the subject, consolidating all relevant information to provide a comprehensive understanding of analyzing ROC curves.

The fundamental theory of ROC curves:
The book begins by exploring the relationship between ROC curves and a range of performance measures. It then extends the theory into practice, detailing the estimation of ROC curves. Building upon this foundation, the authors present statistical tests for ROC curves and their summary statistics. They delve into the impact of covariates on ROC curves, examine the crucial special problem of comparing two ROC curves, and explore Bayesian methods for ROC analysis.

Special topics:
The text then delves into extensions of the basic analysis to handle more complex scenarios, such as combining multiple ROC curves and addressing issues arising from the presence of more than two classes. Focusing on design and interpretation aspects, it covers topics such as missing data, verification bias, sample size determination, designing ROC studies, and selecting the optimal threshold from the ROC curve. The final chapter showcases applications that not only illustrate these techniques but also demonstrate the broad applicability of ROC analysis across different disciplines.

With nearly 5,000 articles published to date on ROC analysis, the explosive interest in ROC curves and their analysis is expected to persist in the foreseeable future. In response to this growing interest, this timely book will undoubtedly serve as a valuable guide for both current and future users of ROC analysis.

Weight: 470g
Dimension: 234 x 156 (mm)
ISBN-13: 9781032477732