A non-parametric method for the comparison of partial areas under ROC curves and its application to large health care data sets

• Published in: Statistics in medicine Vol. 21; no. 5; pp. 701 - 715
• Main Authors: Zhang, Dong D., Zhou, Xia-Hua, Freeman Jr, Daniel H., Freeman, Jean L.
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 15.03.2002; Wiley
• Subjects: Area Under Curve; area under ROC curve; Biological and medical sciences; breast cancer; Breast Neoplasms - diagnosis; Breast Neoplasms - economics; Breast Neoplasms - epidemiology; Breast Neoplasms - therapy; Computerized, statistical medical data processing and models in biomedicine; Epidemiology; Female; Humans; Medical sciences; Medical statistics; Medicare - statistics & numerical data; medicare claims; Models, Statistical; non-parametric method; portions of two ROC curves; ROC Curve; Statistics, Nonparametric; Tumors; Human; Non parametric method; Malignant tumor; Epidemiology; Statistical method; Mammary gland diseases; Logistic regression; Sensitivity; Specificity; Receiver operating characteristic curves; Predictive value; Curved surface; Mammary gland; Medical application; Survival curve; Comparative study
• ISSN: 0277-6715; 1097-0258
• DOI: 10.1002/sim.1011

The receiver operating characteristic (ROC) curve is a statistical tool for evaluating the accuracy of diagnostic tests. Investigators often compare the validity of two tests based on the estimated areas under the respective ROC curves. However, the traditional way of comparing entire areas under two ROC curves is not sensitive when two ROC curves cross each other. Also, there are some cutpoints on the ROC curves that are not considered in practice because their corresponding sensitivities or specificities are unacceptable. For the purpose of comparing the partial area under the curve (AUC) within a specific range of specificity for two correlated ROC curves, a non‐parametric method based on Mann–Whitney U‐statistics has been developed. The estimation of AUC along with its estimated variance and covariance is simplified by a method of grouping the observations according to their cutpoint values. The method is used to evaluate alternative logistic regression models that predict whether a subject has incident breast cancer based on information in Medicare claims data. Copyright © 2002 John Wiley & Sons, Ltd.