Transformed Dynamic Quantile Regression on Censored Data

We propose a class of power-transformed linear quantile regression models for time-to-event observations subject to censoring. By introducing a process of power transformation with different transformation parameters at individual quantile levels, our framework relaxes the assumption of logarithmic transformation on survival times and provides dynamic estimation of various quantile levels. With such formulation, our proposal no longer requires the potentially restrictive global linearity assumption imposed on a class of existing inference procedures for censored quantile regression. Uniform consistency and weak convergence of the proposed estimator as a process of quantile levels are established via the martingale-based argument. Numerical studies are presented to illustrate the outperformance of the proposed estimator over existing contenders under various settings.