Linearly admissible estimators of mean vector with respect to balanced loss function in multivariate statistics. Issue 4 (16th February 2016)

• Record Type: Journal Article
• Authors: Cao, Ming-Xiang; Shena, Guang-Jun
• Is Part Of: Communications in statistics. Volume 45:Issue 4(2016)
• Page Start: 1063
• Page End: 1069
• Publication Date: 2016-02-16
• Subjects: Admissibility -- Balanced loss function -- Linear estimators -- Mean vector -- Multivariate statistics; Primary 62J12 -- Secondary 62C15.; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2013.854912
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: Let X 1, X 2, …, X n be random samples from a probability model with mean vector β and covariance matrix Σ where both and Σ > 0 are unknown. Zellner's balanced loss function is adopted to estimate β. Sufficient and necessary conditions for linear estimators to be admissible in classes of homogeneous and non homogeneous linear estimators are obtained, respectively, which extend the results of Xu(1996) .