Generalized Ridge and Principal Correlation Estimator of the Regression Parameters and Its Optimality
Received:May 28, 2007  Revised:March 10, 2009
Key Word: linear regression model   generalized ridge and principal correlation estimator   mean squares error   Pitman closeness criterion.  
Fund ProjectL:the National Natural Science Foundation of China (Nos.60736047; 10671007; 60772036); the Foundation of Beijing Jiaotong University (Nos.2006XM037; 2007XM046).
Author NameAffiliation
GUO Wen Xing School of Science, Beijing Jiaotong University, Beijing 100044, China 
ZHANG Shang Li School of Science, Beijing Jiaotong University, Beijing 100044, China 
XUE Xiao Wei School of Science, Beijing Jiaotong University, Beijing 100044, China 
Hits: 2380
Download times: 1409
Abstract:
      In this paper, we propose a new biased estimator of the regression parameters, the generalized ridge and principal correlation estimator. We present its some properties and prove that it is superior to LSE (least squares estimator), principal correlation estimator, ridge and principal correlation estimator under MSE (mean squares error) and PMC (Pitman closeness) criterion, respectively.
Citation:
DOI:10.3770/j.issn:1000-341X.2009.05.014
View Full Text  View/Add Comment  Download reader