Skip Internal Navigation
EB Research - Methodological Research in Epidemiology
Receiver Operating Characteristic (ROC) Curves
The receiver operating characteristic (ROC) curve is a useful and widely used analytical tool for assessing a biomarker's usefulness in distinguishing individuals with and without disease. An extensive literature exists for its estimation and application. Researchers here have made significant contributions to this literature in the following areas:
- Estimating the ROC curve and summary measures accounting for various sources of measurement error
- Using maximum likelihood under various distributional assumptions in both univariate and multivariate settings
- Estimating the ROC curve and summary measures from measurements based on a pooling and hybrid design
- Assessing efficiency and robustness of various techniques
This continued research will allow development and analysis of biomarkers under a wide variety of real world limitations and complications.
Principal Investigator
Enrique F. Schisterman, Ph.D. & Neil Perkins, Ph.D.
DESPR Collaborators
Selected Publications
- Perkins NJ, Schisterman EF, Vexler A. ROC curve inference for best linear combination of two biomarkers subject to limits of detection. Biometrical Journal 2011; 53: 464-76. PMID: 22223252
- Perkins NJ, Schisterman EF, & Vexler A. (2009). Generalized ROC curve inference for a biomarker subject to a limit of detection and measurement error. Statistics in Medicine, 28, 1841-1860. PMID: 19340817
- Ruopp MD, Perkins NJ, Whitcomb BW, & Schisterman EF. (2008). Youden index and optimal cut-point estimated from observations subject to a lower limit of detection. Biometrical Journal, 50, 419-430. PMID: 18435502
- Mumford SL, Schisterman EF, Vexler A, & Liu A. (2006). Pooling biospecimens and limits of detection: effects on ROC curve analysis. Biostatistics, 7, 585-598. PMID: 16531470
- Perkins NJ & Schisterman EF. (2006). The inconsistency of "optimal" cutpoints obtained using two criteria based on the receiver operating characteristic curve. American Journal of Epidemiology, 163, 670-675. PMID: 16410346