Title: Induced smoothed methods in analysis of semiparametric quantile residual lifetimes models
Authors: Sangwook Kang - Yonsei University (Korea, South) [presenting]
Kyuhyun Kim - Yonsei University (Korea, South)
Abstract: The focus is on statistical inference procedures for fitting a semiparametric quantile residual life (SQRL) model that models life expectancy. Quantile residual lifetimes are essential summary measures in survival analysis along with a hazard function or survival function. Recent statistical inference procedures for fitting SQRL models have been estimating functions approaches that is nonsmooth in model parameters. Thus, optimizing objective functions or solving estimating equations could be very cumbersome. We propose to employ a computationally-efficient induced-smoothing procedure that smoothes nonsmooth estimating functions. Variance estimation can be done via efficient resampling procedures that uses the sandwich form of asymptotic variances. We establish the consistency and asymptotic normality of the proposed estimators. Finite sample properties are investigated via an extensive simulations studies. We illustrate our proposed methods with a real dataset.