CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: Envelopes for censored quantile regression Authors:  Yue Zhao - KU Leuven (Belgium) [presenting]
Shanshan Ding - University of Delaware (United States)
Ingrid Van Keilegom - KU Leuven (Belgium)
Zhihua Su - University of Florida (United States)
Abstract: Quantile regression has emerged as a powerful tool for survival analysis with censored data. We propose an efficient estimator for the coefficients in quantile regression with censored data using the envelope model. The envelope model uses dimension reduction techniques to identify material and immaterial components in the data, and forms the estimator of the regression coefficient based only on the material component, thus reducing the variability of the estimation. We will derive asymptotic properties of the proposed estimator and demonstrate its efficiency gains compared to the traditional estimator for the quantile regression with censored data. Recent advances in algorithms for the envelope model allow for efficient implementation of the proposed method. The strength of our proposed method is demonstrated via simulation studies.