Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 402 - Statistical Methods for New Challenges in Lifetime/Complex Data
Type: Topic Contributed
Date/Time: Wednesday, August 5, 2020 : 1:00 PM to 2:50 PM
Sponsor: Lifetime Data Science Section
Abstract #310983
Title: Locally Homogeneous Censored Quantile Regression Model with Time-Dependent Covariates
Author(s): Tony Sit*
Companies: The Chinese University of Hong Kong
Keywords: Quantile regression; Survival anslysis; Time-dependent variable

Traditionally, censored quantile regression stipulates a specific, pointwise conditional quantile of the survival time given covariates. Despite its popularity owing to model flexibility and straightforward interpretation, the pointwise formulation oftentimes yields rather unstable estimates across neighbouring quantile levels with substantially large variances. In view of this phenomenon, we propose a new class of censored quantile regression models with time-dependent covariates that can capture the relationship between the failure time and the covariate processes of a target population that falls within a specific percentile bracket. The pooling of information within a homogeneous neighbourhood facilitates more stable, hence more efficient, estimates. Numerical studies demonstrate that the proposed estimator outperforms current alternatives under various settings in terms of smaller empirical bias and standard deviation. A perturbation-based resampling method is also provided to reconcile the asymptotic distribution of the parameter estimates. Finally, consistency and weak convergence of the proposed estimator are established via empirical process theory.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program