Notes on the Extended Class of Stein Estimators

Abstract

An estimator in the extended class of Stein estimators has two undesirable properties. For a small value of prior guess, it ignores the data. Moreover, for some cases its risk is not uniformly smaller than that of Stein estimator. We show that there exists a lower bound on tau (S) to guarantee a smaller risk, and the resulting estimator does not ignore the data.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1986
Accession Number
ADA171242

Entities

People

  • Suk-ki Hahn

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Bayesian Networks
  • Classification
  • Data Science
  • Distribution Functions
  • Estimators
  • Guarantees
  • Information Science
  • Military Research
  • Normal Distribution
  • Probability
  • Random Variables
  • Security
  • Statistical Algorithms
  • Statistical Inference
  • Statistics
  • Universities

Fields of Study

  • Mathematics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Strategic Security Studies