Robustness of Minimum Norm Quadratic Unbiased Estimator of Variance for the General Linear Model
Received:May 05, 2001  
Key Words: general linear model   generalized inverse   orthogonal projector   minimum norm quadratic unbiased estimator  
Fund Project:Supported by China Mathematics Tian Yuan Youth Foundation (10226024) and China Postdoctoral Science Foundation.
Author NameAffiliation
LI Shu-you Dept. of Math. Phys.
Liaoning Institute of Technology
Jinzhou
China 
ZHANG Bao-xue Dept. of Math
Beijing Institute of Technology
Beijing
China
Dept. of Statistics
Northeast Normal University Jilin
China 
Hits: 2234
Download times: 1432
Abstract:
      In this paper, necessary and sufficient conditions for equalities between α2y1(I-PX)y and σ2 under the general linear model, where and α2 is a known positive number, are derived. Furthermore, when the Gauss-Markov estimators and the ordinary least squares estimators are identical, we obtain a simple equivalent condition.
Citation:
DOI:10.3770/j.issn:1000-341X.2004.02.015
View Full Text  View/Add Comment