Statistical Methods in Diagnostic Medicine

Statistical Methods in Diagnostic Medicine provides a comprehensive account of statistical methods for the design and analysis of diagnostic studies. Brought fully up to date, this new edition includes discussion of a range of newly published methods that are relevant to the evaluation of diagnostic tests. In particular, two new chapters cover the accuracy of diagnostic tests for biomarkers and benefit-risk evaluation of diagnostic and risk prediction tests. The book includes 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. As before, the authors stress common measures of diagnostic accuracy and designs for diagnostic accuracy studies, methods of estimation and hypothesis testing of the accuracy of diagnostic tests, and advanced analytic techniques such as methods for comparing correlated ROC curves in multi-reader studies, correcting verification bias, and correcting imperfect gold standards.