A0789
Title: Prediction accuracy for joint model of interval-censored data and longitudinal markers
Authors: Yang-Jin Kim - Sookmyung Women University (Korea, South) [presenting]
Abstract: Joint model for longitudinal marker and time to event data has been an attractive modeling that provides the association between the risk of an event and the change of makers. The interest is to provide appropriate measures for quantifying the prediction accuracy of the prediction model of interval-censored event time with longitudinal markers. Dynamic versions of AUC (Area Under the Curve) and Brier score to reflect updated information are suggested. The performance of the proposed methods under the finite sample is evaluated with simulation and the paquid dataset is analyzed as a real data example.
