Synopsis
An important role of diagnostic medicine research is to estimate and compare the accuracies of diagnostic tests. This book provides a comprehensive account of statistical methods for design and analysis of diagnostic studies, including sample size calculations, estimation of the accuracy of a diagnostic test, comparison of accuracies of competing diagnostic tests, and regression analysis of diagnostic accuracy data. Discussing recently developed methods for correction of verification bias and imperfect reference bias, methods for analysis of clustered diagnostic accuracy data, and meta-analysis methods, Statistical Methods in Diagnostic Medicine explains:
* Common measures of diagnostic accuracy and designs for diagnostic accuracy studies
* Methods of estimation and hypothesis testing of the accuracy of diagnostic tests
* Meta-analysis
* Advanced analytic techniques-including methods for comparing correlated ROC curves in multi-reader studies, correcting verification bias, and correcting when an imperfect gold standard is used
Thoroughly detailed with numerous applications and end-of-chapter problems as well as a related FTP site providing FORTRAN program listings, data sets, and instructional hints, Statistical Methods in Diagnostic Medicine is a valuable addition to the literature of the field, serving as a much-needed guide for both clinicians and advanced students.
Booknews
Statistical methods for design and analysis of diagnostic studies, including sample size calculations, estimation of the accuracy of a diagnostic test, comparison of accuracies of competing diagnostic tests, and regression analysis of diagnostic accuracy data, are described here for clinicians and advanced students. Some recently developed methods for correction of verification bias and imperfect reference bias, methods for analysis of clustered diagnostic accuracy data, and methods for meta-analysis are also discussed. The intended audience includes clinicians interested in conducting diagnostic studies, statisticians interested in analyzing data from such studies, and statisticians and graduate students conducting statistical research in diagnostic medicine. Zhou is affiliated with the Department of Biostatistics at Indiana University's School of Medicine. Annotation c. Book News, Inc., Portland, OR (booknews.com)