Nonparametric relative error estimation of the regression function for left truncated and right censored time series data

The paper introduces a nonparametric estimator for the regression function of left truncated and right censored data, achieved through minimising the mean squared relative error. Under & alpha;-mixing condition, strong uniform convergence of the estimator is established with a rate over a compact set. An extensive simulation study is conducted to assess the estimator's performance, comparing its efficiency to that of the classical regression estimator for finite samples across various scenarios. Moreover, a real world application is presented to demonstrate the practical utility of the proposed estimator.