Research-Optimal Model Averaging Estimation for Generalized Linear Models

Research

All

Optimal Model Averaging Estimation for Generalized Linear Models

Speaker: ZHANG Xinyu
Time: Jun 14, 2017, 11:05-12:05
Location: Conference Room 415, Wisdom Valley 3#

Abstract:

Considering model averaging estimation in generalized linear models, we propose a weight choice criterion based on the Kullback-Leibler (KL) loss with a penalty term. This criterion is different from that for continuous observations in principle, but reduces to the Mallows criterion in the situation. We prove that the corresponding model averaging estimator is asymptotically optimal under certain assumptions. Numerical experiments illustrate that the proposed method is promising.