题目：

MODEL SELECTION AND MODEL AVERAGING FOR NONLINEAR REGRESSION MODELS

时间：

本周五上午十点（3月24日）

地点：

博识楼434

摘要：

This paper considers the problem of model selection and model averaging for regression models which can be nonlinear in their pa- rameters and variables. We propose a new information criterion called nonlinear model information criterion (NIC), which is proved to be an asymptotically unbiased estimator of the risk function un- der nonlinear settings. We also develop a nonlinear model averaging method (NMA) and extend NIC to NIC MA criterion, which is the corresponding weight choosing criterion for NMA. By taking account of the complexity of model forms into the penalty term, NIC and NIC MA achieve significant gain of performance. The optimality of NMA, convergence of the selected weight and other theoretical prop- erties are proved. Simulation results show that NIC and NMA lead to relatively lower risks compared with alternative model selection and model averaging methods under most situations.

主讲人信息：

• Name: Qingfeng LIU（刘庆丰）
• Current Status: Full Professor, Department of Economics, Otaru University of Commerce. Japan.
• Email: qliu@res.otaru-uc.ac.jp                         
• Fields of Concentration: Econometrics.
• Education:
  • BA (Economics), Niigata University, Japan, March 2002. 
  • MA (Economics), Kyoto University, Japan, March 2004.
  • PhD (Economics), Kyoto University, Japan, March 2007.
  • Postdoctoral Research Fellow, Princeton University, USA, Until October, 2008.