A class of modified stein estimators with easily computable risk functions

Samuel D. Oman*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Consider the problem of estimating the mean of a p (≥3)-variate multi-normal distribution with identity variance-covariance matrix and with unweighted sum of squared error loss. A class of minimax, noncomparable (i.e. no estimate in the class dominates any other estimate in the class) estimates is proposed; the class contains rules dominating the simple James-Stein estimates. The estimates are essentially smoothed versions of the scaled, truncated James-Stein estimates studied by Efron and Morris. Explicit and analytically tractable expressions for their risks are obtained and are used to give guidelines for selecting estimates within the class.

Original languageEnglish
Pages (from-to)359-369
Number of pages11
JournalJournal of Statistical Planning and Inference
Volume7
Issue number4
DOIs
StatePublished - Jun 1983

Keywords

  • Multivariate normal mean
  • Stein estimates.

Fingerprint

Dive into the research topics of 'A class of modified stein estimators with easily computable risk functions'. Together they form a unique fingerprint.

Cite this