Optimism Correction of the AUC with Complex Survey Data

Special statistical techniques are required to develop valid prediction models for complex survey data. Recently, a weighted estimator has been proposed to estimate the area under the receiver operating characteristic curve in this context. However, the proposed estimator has shown an optimistic behaviour. Thus, the goal of this work is to analyze the performance of replicate weights methods to correct for the optimism of the AUC in the context of complex survey data.