Asymptotic Properties of the Sequential Empirical ROC and PPV Curves
Download the Paper Forward to a colleague
Abstract:
The receiver operating characteristic (ROC) curve and the positive predictive value (PPV) curve are two common measures of performance for a diagnostic biomarker. The independent increments covariance structure assumption is common in the group sequential study design literature. Showing that summary measures of the ROC and PPV curves have an independent increments covariance structure will provide flexibility when designing group sequential diagnostic biomarker studies. The ROC and PPV curves are often estimated empirically to avoid assumptions about the distributional form of the biomarkers. In this paper we derive asymptotic theory for the sequential empirical ROC and PPV curves. These results are used to show that the independent increments assumption holds for some summary measures of the ROC and PPV curves when estimated empirically.
Subject Area:
Statistical Theory and Methods
Suggested Citation:
Joseph S. Koopmeiners and Ziding Feng, "Asymptotic Properties of the Sequential Empirical ROC and PPV Curves" (April 24, 2009). UW Biostatistics Working Paper Series. Working Paper 345.
http://www.bepress.com/uwbiostat/paper345