Inadmissibility of the Best Equivariant Estimator of the Variance-Covariance Matrix, the Precision Matrix, and the Generalized Variance: A Study.

Abstract

Based on a data matrix X = (X1,...,X sub k): p x k with independent columns X sub i approximately N sub p (Xi sub i, Sigma), and an independent p x p Wishart matrix S approximately W sub p (n, Sigma), procedures to obtain estimators dominating the best equivariant estimators of (Sigma, 1/Sigma and abs. val. under various loss functions are reviewed. Keywords: Best equivariant estimator; squared error loss; entropy loss; generalized variance; MANOVA test; Roy's maximum root test; testimator; minimax estimator; Wishart distribution; Wishart identity.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1986
Accession Number
ADA177099

Entities

People

  • Bismal K. Sinha

Organizations

  • University of Pittsburgh

Tags

Communities of Interest

  • C4I
  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Contracts
  • Coordinate Systems
  • Covariance
  • Data Science
  • Estimators
  • Governments
  • Identities
  • Information Science
  • Multivariate Analysis
  • Scientific Research
  • Statistical Algorithms
  • Statistics
  • Surveys
  • United States
  • United States Government
  • Wishart Matrices

Fields of Study

  • Mathematics

Readers

  • Analytical Mechanics
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms