Variable selection in expectile regression

ABSTRACT

In this paper, we consider penalized linear expectile regression using SCAD penalty function. We prove that our estimator has not only consistency but also oracle properties. In order to perform a better statistical inference, we make a correction of our estimator. The performance of our proposed methods are investigated through simulation studies.

Keywords:

• Expectile regression
• SCAD
• statistical inference
• variable selection.

MATHEMATICS SUBJECT CLASSIFICATION:

• 62J99
• 62F12
• 62F25

Acknowledgments

This research is partly supported by the Fundamental Research Funds for the Central Universities, Major Project of the National Social Science Foundation of China (No. 13&ZD163), Zhejiang Provincial Natural Science Foundation (No: LY18A010005) and the Research Project of Humanities and Social Science of Ministry of Education of China (No. 17YJA910003).