A Stochastic Restricted $s$--$K$ Estimator in the Linear Model
Received:July 08, 2013  Revised:November 13, 2013
Key Words: the ordinary mixed estimator   $s$--$K$ estimator   stochastic restricted $s$--$K$ estimator   the mean squared error matrix.  
Fund Project:Supported by the National Natural Science Foundation of China (Grant No.11201005), the Natural Science Foundation of Anhui Province (Grant No.1308085QA13), the Key Project of Distinguished Young Talents of Universities in Anhui Province (Grant No.2012SQRL028ZD) and the Key Project of Natural Science Foundation of Universities in Anhui Province (Grant No.KJ2012A135).
Author NameAffiliation
Daojiang HE School of Mathematics and Computer Science, Anhui Normal University, Anhui 241003, P. R. China 
Yan WU School of Mathematics and Computer Science, Anhui Normal University, Anhui 241003, P. R. China 
Hits: 2386
Download times: 2126
Abstract:
      In this paper, we propose a stochastic restricted $s$--$K$ estimator in the linear model with additional stochastic linear restrictions by combining the ordinary mixed estimator (OME) with the $s$--$K$ estimator. It is shown that the proposed estimator is superior to the OME and the $s$--$K$ estimator under the mean squared error matrix criterion under some conditions. Finally, a numerical example and a Monte Carlo simulation study are given to verify the theoretical results.
Citation:
DOI:10.3770/j.issn:2095-2651.2014.03.013
View Full Text  View/Add Comment