EcoSta 2018: Registration
View Submission - EcoSta2018
A0348
Title: Locally weighted regression quantiles with competing risks Authors:  Sangbum Choi - Korea University (Korea, South) [presenting]
Abstract: Flexible estimation and inference procedures are considered for competing risks quantile regression that not only provide meaningful interpretations by using cumulative incidence quantiles, but also extend the conventional accelerated failure time model by relaxing some of the stringent model assumptions such as global linearity and unconditional independence. The locally weighed technique for censored quantile regressions is extended to the competing risks setting. The proposed procedure permits the fast and accurate computation of quantile regression parameter estimates and standard variances by using conventional numerical methods. Numerical studies show that the proposed estimators perform well and the resulting inference is reliable in practical settings. The method is finally applied to data from a soft tissue sarcoma study.