Admissibility under the Frequentist′s Validity Constraint in Estimating the Loss of the Least-Squares Estimator

✍ Scribed by F.S. Hsieh; J.T.G. Hwang

• Publisher: Elsevier Science
• Year: 1993
• Tongue: English
• Weight: 238 KB
• Volume: 44
• Category: Article
• ISSN: 0047-259X
• DOI: 10.1006/jmva.1993.1016

✦ Synopsis

We consider the problem of estimating the sum of squared error loss (L=|\beta-\hat{\beta}|^{2}) of the least-squares esitmator (\hat{\beta}) for (\beta), the regression coefficient. The standard estimator (\ell_{0}) is the expected value of (L). Here the error variance is assumed to be known. Previous results of Johnstone (1988. In Statistical Dectision Theory and Reluted Topics If (S. Gupta and J. Berger. Eds.). 1. 361-379, Springer-Verlag, New York , show that (\hat{L}{0}) is inadmissible under the loss ((\hat{L}-L)^{2}) if the dimension of (\hat{\beta}) is five or more. However, since we are estimating the loss, a typical frequentist principle will lead to the usage of estimators which are frequentist valid. Johnston's improved esitmator. however. violates this principle. In this paper, we prove that it is impossible to improve upon (\hat{L}{0}) among the class of frequentist valid estimators. The work parallels Hwang and Brown (1991, Ann. Statist. 10 1964-1977) for the corresponding confidence set problems, although the argument is entirely different and much simpler. ‘ 1993 Academic Press. Inc.