Model Averaging Based on Kullback-Leibler Distance

Posted: 12 Oct 2012

See all articles by Xinyu Zhang

Xinyu Zhang

Chinese Academy of Sciences (CAS) - Academy of Mathematics and Systems Sciences

Guohua Zou

Chinese Academy of Sciences - Academy of Mathematics and Systems Science

Date Written: October 11, 2012

Abstract

Model averaging is an alternative of model selection for dealing with model uncertainty. This paper proposes a model averaging procedure based on an unbiased estimator of the expected Kullback-Leibler distance. The resulting model average estimator is proved to be asymptotically optimal. When combining the least squares estimators, the model average estimator has the same large sample property as Mallows model average (MMA) estimator developed by Hansen (2007). A modified version of the model average estimator is also suggested for the case of heteroscedastic random errors. Simulation study shows that the proposed model average estimators perform better than some other existing model average estimators in literature and selected estimator by the corrected Akaike information criterion. Our new methods are further applied to analyzing two real-world datasets.

Keywords: akaike information, Kullback-Leibler distance, model averaging

JEL Classification: C51, C52

Suggested Citation

Zhang, Xinyu and Zou, Guohua, Model Averaging Based on Kullback-Leibler Distance (October 11, 2012). Available at SSRN: https://ssrn.com/abstract=2160119 or http://dx.doi.org/10.2139/ssrn.2160119

Xinyu Zhang (Contact Author)

Chinese Academy of Sciences (CAS) - Academy of Mathematics and Systems Sciences ( email )

Zhong-Guan-Cun-Dong-Lu 55, Haidian District
Beijing, 100190, P.R., Beijing 100190
China

Guohua Zou

Chinese Academy of Sciences - Academy of Mathematics and Systems Science ( email )

52 Sanlihe Rd.
Datun Road, Anwai
Beijing, Xicheng District 100864
China

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
1,114
PlumX Metrics