Jackknife model averaging for additive expectile prediction

Abstract

In the past 20 years, model averaging has been developed as a better tool than model selection in statistical prediction. Expectile prediction is widely used for modeling data with the heterogeneous conditional distribution. In this article, we introduce a model averaging estimator for additive expectile prediction. The resulting model averaging estimator is shown to have asymptotic optimality under some regular conditions. Simulation experiments are conducted to demonstrate that the performance of our method is better than that of other common model selection and model averaging methods under the finite-sample case. Our method is also verified in the house and wage datasets.

Keywords:

• Model averaging
• expectile regression
• final prediction error
• jackknife criterion

AMS Subject Classification:

• 62G08
• 62G05

Acknowledgments

The authers thank the Editor, the Associate Editor and the referees for their constructive comments.

Disclosure statement

No potential conflict of interest was reported by the authors.

Supplemental material

Following the reviewers suggestions, we conduct three additional simulation experiments.

Additional information

Funding

Xianwen Sun and Lixin Zhang’s research was supported by grants from the NSF of China (Grant No. 11731012, 12031005).