Online Program

Adjustment for Verification Bias in Estimation of the area under ROC curve adjusting for Covariates

Danping Liu, National Institute of Health 
*Xiao-Hua Andrew Zhou, University of Washington 

Keywords: ROC curves, Verification Bias, Covariates, Semiparametric models

In ROC analysis, covariate adjustment is advocated when the covariates impact the magnitude or accuracy of the test under study. Meanwhile, for many large scale screening tests, the true condition status may be subject to missingness because it is expensive and/or invasive to ascertain the disease status. The complete-case analysis may end up with a biased inference, also known as \veri cation bias". To address the issue of covariate adjustment with veri cation bias in ROC analysis, we propose several estimators for the area under the covariate-speci c and covariate- adjusted ROC curves (AUCx and AAUC). The AUCx is directly modelled in the form of binary regression, and the estimating equations are based on the U statistics. The AAUC is estimated from the weighted average of AUCx over the covariate distribution of the diseased subjects. We employ reweighting and imputation techniques to overcome the veri cation bias problem. Our proposed estimators are initially derived assuming that the true disease status is missing at random (MAR), and then with some modi cation, the estimators can be extended to the not-missing-at-random (NMAR) situation. The asymptotic distributions are derived for the proposed estimators. The nite sample performance is evaluated by a series of simulation studies. Our method is applied to a data set in Alzheimer's disease research.