Home > Papers

 
 
Empirical Likelihood Inference for Semiparametric Fixed Effects Models
Li Gaorong 1 *,Zhang Junhua 2,Feng Sanying 1
1.College of Applied Sciences, Beijing University of Technology, Beijing 100124
2.College of Mechanical Engineering, Beijing Information Science and Technology University, Beijing 100192
*Correspondence author
#Submitted by
Subject:
Funding: the Specialized Research Fund for the Doctoral Program of Higher Education of China(No.No. 20101103120016), Training Programme Foundation for the Beijing Municipal Excellent Talents(No.No. 2010D005015000002), Gaorong Li’s research was supported by the National Nature Science Foundation of China (No.No. 11101014), Junhua Zhang’s research was supported by the National Natural Science Foundation of China(No.No. 11002005), Funding Project for Academic Human Resources Development in Institutions of Higher Learning Under the Jurisdiction of Beijing Municipality(No.No. PHR20110822)
Opened online:21 November 2011
Accepted by: none
Citation: Li Gaorong,Zhang Junhua,Feng Sanying.Empirical Likelihood Inference for Semiparametric Fixed Effects Models[OL]. [21 November 2011] http://en.paper.edu.cn/en_releasepaper/content/4449680
 
 
In this article, a partially linear panel data model with fixed effects is considered. Unlike existing empirical likelihood approaches for other simpler models, empirical likelihood method cannot be directly used to construct the confidence region of parameter of interest when the fixed individual effects exist. By using a local linear regression approach and the kernel-based weights, the fixed effects are removed and empirical log-likelihood ratio statistic for the unknown parameter of interest in the model is suggested. It is proved that the proposed statistic is asymptotically standard chi-square distribution under some suitable conditions, and hence it can be used to construct the confidence region of the parameter. A modified "leave-one-subject-out" cross validation method is used to select the optimal bandwidth automatically. A simulation study indicates that, in terms of coverage probabilities and the confidence regions, the proposed method performs better than the profile least-squares method.
Keywords:Empirical likelihood; Fixed effects; Panel data; Partially linear models
 
 
 

For this paper

  • PDF (0B)
  • ● Revision 0   
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags

Add yours

Related Papers

Statistics

PDF Downloaded 368
Bookmarked 0
Recommend 5
Comments Array
Submit your papers