A robust testing procedure for the equality of covariance matrices

Shagufta Aslam, David M Rocke

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In classical statistics the likelihood ratio statistic used in testing hypotheses about covariance matrices does not have a closed form distribution, but asymptotically under strong normality assumptions is a function of the χ2-distribution. This distributional approximation totally fails if the normality assumption is not completely met. In this paper we will present multivariate robust testing procedures for the scatter matrix Σ using S-estimates. We modify the classical likelihood ratio test (LRT) into a robust LRT by substituting the robust estimates in the formula in place of classical estimates. A nonlinear formula is also suggested to approximate the degrees of freedom for the approximated Wishart distribution proposed for S-estimates of the shape matrix Σ. We present simulation results to compare the validity and the efficiency of the robust likelihood test to the classical likelihood test.

Original languageEnglish (US)
Pages (from-to)863-874
Number of pages12
JournalComputational Statistics and Data Analysis
Volume49
Issue number3
DOIs
StatePublished - Jun 1 2005

Fingerprint

Covariance matrix
Equality
Statistics
Likelihood Ratio Test
Normality
Testing
Likelihood
Estimate
Wishart Distribution
Robust Estimate
Testing Hypotheses
Likelihood Ratio Statistic
Scatter
Closed-form
Degree of freedom
Approximation
Simulation
Likelihood ratio test

Keywords

  • Likelihood ratio test
  • S-estimate

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Statistics, Probability and Uncertainty
  • Electrical and Electronic Engineering
  • Computational Mathematics
  • Numerical Analysis
  • Statistics and Probability

Cite this

A robust testing procedure for the equality of covariance matrices. / Aslam, Shagufta; Rocke, David M.

In: Computational Statistics and Data Analysis, Vol. 49, No. 3, 01.06.2005, p. 863-874.

Research output: Contribution to journalArticle

@article{6ecfaac8a8f644e98495c9b1483b9d16,
title = "A robust testing procedure for the equality of covariance matrices",
abstract = "In classical statistics the likelihood ratio statistic used in testing hypotheses about covariance matrices does not have a closed form distribution, but asymptotically under strong normality assumptions is a function of the χ2-distribution. This distributional approximation totally fails if the normality assumption is not completely met. In this paper we will present multivariate robust testing procedures for the scatter matrix Σ using S-estimates. We modify the classical likelihood ratio test (LRT) into a robust LRT by substituting the robust estimates in the formula in place of classical estimates. A nonlinear formula is also suggested to approximate the degrees of freedom for the approximated Wishart distribution proposed for S-estimates of the shape matrix Σ. We present simulation results to compare the validity and the efficiency of the robust likelihood test to the classical likelihood test.",
keywords = "Likelihood ratio test, S-estimate",
author = "Shagufta Aslam and Rocke, {David M}",
year = "2005",
month = "6",
day = "1",
doi = "10.1016/j.csda.2004.06.009",
language = "English (US)",
volume = "49",
pages = "863--874",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - A robust testing procedure for the equality of covariance matrices

AU - Aslam, Shagufta

AU - Rocke, David M

PY - 2005/6/1

Y1 - 2005/6/1

N2 - In classical statistics the likelihood ratio statistic used in testing hypotheses about covariance matrices does not have a closed form distribution, but asymptotically under strong normality assumptions is a function of the χ2-distribution. This distributional approximation totally fails if the normality assumption is not completely met. In this paper we will present multivariate robust testing procedures for the scatter matrix Σ using S-estimates. We modify the classical likelihood ratio test (LRT) into a robust LRT by substituting the robust estimates in the formula in place of classical estimates. A nonlinear formula is also suggested to approximate the degrees of freedom for the approximated Wishart distribution proposed for S-estimates of the shape matrix Σ. We present simulation results to compare the validity and the efficiency of the robust likelihood test to the classical likelihood test.

AB - In classical statistics the likelihood ratio statistic used in testing hypotheses about covariance matrices does not have a closed form distribution, but asymptotically under strong normality assumptions is a function of the χ2-distribution. This distributional approximation totally fails if the normality assumption is not completely met. In this paper we will present multivariate robust testing procedures for the scatter matrix Σ using S-estimates. We modify the classical likelihood ratio test (LRT) into a robust LRT by substituting the robust estimates in the formula in place of classical estimates. A nonlinear formula is also suggested to approximate the degrees of freedom for the approximated Wishart distribution proposed for S-estimates of the shape matrix Σ. We present simulation results to compare the validity and the efficiency of the robust likelihood test to the classical likelihood test.

KW - Likelihood ratio test

KW - S-estimate

UR - http://www.scopus.com/inward/record.url?scp=18744375160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18744375160&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2004.06.009

DO - 10.1016/j.csda.2004.06.009

M3 - Article

AN - SCOPUS:18744375160

VL - 49

SP - 863

EP - 874

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 3

ER -