A0342
Title: Semiparametric accelerated failure time model with interval-censored data under outcome-dependent sampling design
Authors: Tsui-Shan Lu - National Taiwan Normal University (Taiwan) [presenting]
Abstract: In epidemiological studies or clinical trials, it is always of interest to discuss the relationship between the failure time of a certain disease and other possible exposure measurements, while in the meantime the researchers are in favor of cost-effective study designs. We consider complete interval-censored data collected under an outcome-dependent sampling (ODS) design and the semiparametric accelerated failure time (AFT) model for parameter estimation, which directly links the failure time to the covariates through a log-linear model without specifying the error distribution. We conducted extensive simulation studies to assess the performance of the proposed estimators under various settings and applied our methods to a real data set derived from a coronary heart disease study from National Taiwan Hospital.
