Least Squares Regression Methods for Clustered ROC Data with Discrete Covariates

• Activity Number: 323
• Type: Contributed
• Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
• Sponsor: Health Policy Statistics Section
• Author(s): Liansheng Tang* and Wei Zhang and Qizhai Li and Xuan Ye and Leighton Chan
• Companies: George Mason University/National Institutes of Health and Chinese Academy of Sciences and Chinese Academy of Sciences and George Mason University/FDA and National Institutes of Health
• Keywords: ROC ; least squares ; clustered

Abstract

The receiver operating characteristic (ROC) curve is a popular tool to evaluate and compare the accuracy of diagnostic tests to distinguish the diseased group from the non-diseased group when test results from tests are continuous or ordinal. A complicated data setting occurs when multiple tests are measured on abnormal and normal locations from the same subject and the measurements are clustered within the subject. Although least squares regression methods can be used for the estimation of ROC curve from correlated data, how to develop the least squares methods to estimate the ROC curve from the clustered data has not been studied. Also, the statistical properties of the least squares methods under the clustering setting are unknown. We develop the least squares ROC methods to allow the baseline and link functions to differ, and more importantly, to accommodate clustered data with discrete covariates. We apply the methods to a real example in the detection of glaucomatous deterioration. We also derive the asymptotic properties of the proposed methods.