Estimation of Non-Linear Expectile Regression Model with Censoring Indicators Missing at Random

Abstract

The present paper focuses on the expectile regression for a non-linear model with right-censored responses and censoring indicators that are missing at random (MAR). Firstly, a calibration estimator and an imputation estimator are constructed for the non-linear expectile regression model. Secondly, under specific regularity conditions, the asymptotic normality of the estimators is established. The validity of the proposed estimation methods is finally verified through simulation and numerical experiments.