Journal of East China Normal University(Natural Sc ›› 2004, Vol. 2004 ›› Issue (1): 40-44.

• Article • Previous Articles     Next Articles

Comparison of MINQUE and Simple Estimator of Covariance Matrix

Abdul-Hussein Saber AL MODEL   

  1. Department of Statistics,East China Normal Unitxrsity, Shanghai 200062, China
  • Received:2002-09-04 Revised:2002-11-11 Online:2004-03-25 Published:2004-03-25
  • Contact: Abdul-Hussein Saber AL MODEL

Abstract: This paper considers comparison of MINQUE and simple estimator of ∑ in the multivariate normal linear model Y~N(XB,∑⊙V) under the risk of squared loss function criterion, where the design matrix X need not have full rank and the dispersion matrix V can be singular. A necessary and sufficient condition is obtained.

Key words: MINQUE, risk, squared loss function, multivariate linear model, MINQUE, risk, squared loss function

CLC Number: