A comparison of estimators of a common correlation coefficient

Research output: Contribution to journalArticle

Abstract

It is often of interest to test the hypothesis that all off-diagonal elements of the correlation matrix of a multivariate normal distribution are equal. If the hypothesis of equal correlation can be accepted, it then may be of interest to estimate the common correlation coefficient. In this paper, four estimators of the common correlation are compared in terms of bias, variance, mean squared error, adequacy of the normal approximation, and ease of calculation. The average sample correlation is seen to be comparable to the other estimators and is recommended here since it is the easiest to calculate. The estimators are compared using simulation.

Original languageEnglish (US)
Pages (from-to)531-543
Number of pages13
JournalCommunications in Statistics - Simulation and Computation
Volume15
Issue number2
DOIs
StatePublished - Jan 1 1986
Externally publishedYes

Fingerprint

Normal distribution
Correlation coefficient
Estimator
Multivariate Normal Distribution
Normal Approximation
Correlation Matrix
Mean Squared Error
Calculate
Estimate
Simulation

Keywords

  • CPU time
  • Fisher z-transform
  • correlation matrix
  • equicorrelation
  • mean squared error
  • normal approximation

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

A comparison of estimators of a common correlation coefficient. / Looney, Stephen Warwick.

In: Communications in Statistics - Simulation and Computation, Vol. 15, No. 2, 01.01.1986, p. 531-543.

Research output: Contribution to journalArticle

@article{00b7aa4eb2554f0c958becc8a652b273,
title = "A comparison of estimators of a common correlation coefficient",
abstract = "It is often of interest to test the hypothesis that all off-diagonal elements of the correlation matrix of a multivariate normal distribution are equal. If the hypothesis of equal correlation can be accepted, it then may be of interest to estimate the common correlation coefficient. In this paper, four estimators of the common correlation are compared in terms of bias, variance, mean squared error, adequacy of the normal approximation, and ease of calculation. The average sample correlation is seen to be comparable to the other estimators and is recommended here since it is the easiest to calculate. The estimators are compared using simulation.",
keywords = "CPU time, Fisher z-transform, correlation matrix, equicorrelation, mean squared error, normal approximation",
author = "Looney, {Stephen Warwick}",
year = "1986",
month = "1",
day = "1",
doi = "10.1080/03610918608812523",
language = "English (US)",
volume = "15",
pages = "531--543",
journal = "Communications in Statistics: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - A comparison of estimators of a common correlation coefficient

AU - Looney, Stephen Warwick

PY - 1986/1/1

Y1 - 1986/1/1

N2 - It is often of interest to test the hypothesis that all off-diagonal elements of the correlation matrix of a multivariate normal distribution are equal. If the hypothesis of equal correlation can be accepted, it then may be of interest to estimate the common correlation coefficient. In this paper, four estimators of the common correlation are compared in terms of bias, variance, mean squared error, adequacy of the normal approximation, and ease of calculation. The average sample correlation is seen to be comparable to the other estimators and is recommended here since it is the easiest to calculate. The estimators are compared using simulation.

AB - It is often of interest to test the hypothesis that all off-diagonal elements of the correlation matrix of a multivariate normal distribution are equal. If the hypothesis of equal correlation can be accepted, it then may be of interest to estimate the common correlation coefficient. In this paper, four estimators of the common correlation are compared in terms of bias, variance, mean squared error, adequacy of the normal approximation, and ease of calculation. The average sample correlation is seen to be comparable to the other estimators and is recommended here since it is the easiest to calculate. The estimators are compared using simulation.

KW - CPU time

KW - Fisher z-transform

KW - correlation matrix

KW - equicorrelation

KW - mean squared error

KW - normal approximation

UR - http://www.scopus.com/inward/record.url?scp=84950206590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950206590&partnerID=8YFLogxK

U2 - 10.1080/03610918608812523

DO - 10.1080/03610918608812523

M3 - Article

VL - 15

SP - 531

EP - 543

JO - Communications in Statistics: Simulation and Computation

JF - Communications in Statistics: Simulation and Computation

SN - 0361-0918

IS - 2

ER -