Abstract
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 α-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.
Acknowledgments
The authors are grateful to the two anonymous referees and associate-editor whose careful reading gave us the opportunity to improve the quality of the first version of the paper and add simulation with real data.
Disclosure statement
No potential conflict of interest was reported by the author(s).