A REMARK ON TESTING SIGNIFICANCE OF AN OBSERVED CORRELATION MATRIX

Shande Chen And, Govind S. Mudholkar

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A simple test for the diagonality of the covariance matrix of a multi‐variate normal population is proposed. The test, which is based upon the sum of squares of the z‐transforms of the sample correlations, is seen to compare well with the current tests in terms of both the null distribution approximations and the powers.

Original languageEnglish
Pages (from-to)105-110
Number of pages6
JournalAustralian Journal of Statistics
Volume31
Issue number1
DOIs
StatePublished - Mar 1989

Fingerprint

Correlation Matrix
Testing
Normal Population
Multivariate Normal
Null Distribution
Sum of squares
Covariance matrix
Approximation

Keywords

  • complete independence
  • pairwise independent correlations
  • x approximation
  • z‐transformation

Cite this

And, Shande Chen ; Mudholkar, Govind S. / A REMARK ON TESTING SIGNIFICANCE OF AN OBSERVED CORRELATION MATRIX. In: Australian Journal of Statistics. 1989 ; Vol. 31, No. 1. pp. 105-110.
@article{f0b600a745a441d6bc6aad9251ae13da,
title = "A REMARK ON TESTING SIGNIFICANCE OF AN OBSERVED CORRELATION MATRIX",
abstract = "A simple test for the diagonality of the covariance matrix of a multi‐variate normal population is proposed. The test, which is based upon the sum of squares of the z‐transforms of the sample correlations, is seen to compare well with the current tests in terms of both the null distribution approximations and the powers.",
keywords = "complete independence, pairwise independent correlations, x approximation, z‐transformation",
author = "And, {Shande Chen} and Mudholkar, {Govind S.}",
year = "1989",
month = "3",
doi = "10.1111/j.1467-842X.1989.tb00503.x",
language = "English",
volume = "31",
pages = "105--110",
journal = "Australian Journal of Statistics",
issn = "0004-9581",
publisher = "Wiley-Blackwell Publishing Ltd",
number = "1",

}

A REMARK ON TESTING SIGNIFICANCE OF AN OBSERVED CORRELATION MATRIX. / And, Shande Chen; Mudholkar, Govind S.

In: Australian Journal of Statistics, Vol. 31, No. 1, 03.1989, p. 105-110.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A REMARK ON TESTING SIGNIFICANCE OF AN OBSERVED CORRELATION MATRIX

AU - And, Shande Chen

AU - Mudholkar, Govind S.

PY - 1989/3

Y1 - 1989/3

N2 - A simple test for the diagonality of the covariance matrix of a multi‐variate normal population is proposed. The test, which is based upon the sum of squares of the z‐transforms of the sample correlations, is seen to compare well with the current tests in terms of both the null distribution approximations and the powers.

AB - A simple test for the diagonality of the covariance matrix of a multi‐variate normal population is proposed. The test, which is based upon the sum of squares of the z‐transforms of the sample correlations, is seen to compare well with the current tests in terms of both the null distribution approximations and the powers.

KW - complete independence

KW - pairwise independent correlations

KW - x approximation

KW - z‐transformation

UR - http://www.scopus.com/inward/record.url?scp=84985516501&partnerID=8YFLogxK

U2 - 10.1111/j.1467-842X.1989.tb00503.x

DO - 10.1111/j.1467-842X.1989.tb00503.x

M3 - Article

AN - SCOPUS:84985516501

VL - 31

SP - 105

EP - 110

JO - Australian Journal of Statistics

JF - Australian Journal of Statistics

SN - 0004-9581

IS - 1

ER -