Diagnostic limitations of skewness coefficients in assessing departures from univariate and multivariate normality

Ronald L. Horswell, Stephen Warwick Looney

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

While many tests of univariate and multivariate normality have been proposed, those based on skewness and kurtosis coefficients are widely presumed to offer the advantage of diagnosing how distributions depart from normality. However, results summarized from many Monte Carlo studies show that tests based on skewness coefficients do not reliably discriminate between skewed and non-skewed distributions. Indeed, the use of skewness tests to discriminate between these distributions lacks theoretical foundation. The performance of skewness tests is shown to be very sensitive to the kurtosis of the underlying distribution.

Original languageEnglish (US)
Pages (from-to)437-459
Number of pages23
JournalCommunications in Statistics - Simulation and Computation
Volume22
Issue number2
DOIs
StatePublished - Jan 1 1993
Externally publishedYes

Fingerprint

Multivariate Normality
Skewness
Univariate
Diagnostics
Kurtosis
Coefficient
Monte Carlo Study
Normality

Keywords

  • kurtosis
  • multivariate
  • normality
  • radii
  • skewness
  • univariate normality

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

@article{49c557f554124495a5b15cc20568079b,
title = "Diagnostic limitations of skewness coefficients in assessing departures from univariate and multivariate normality",
abstract = "While many tests of univariate and multivariate normality have been proposed, those based on skewness and kurtosis coefficients are widely presumed to offer the advantage of diagnosing how distributions depart from normality. However, results summarized from many Monte Carlo studies show that tests based on skewness coefficients do not reliably discriminate between skewed and non-skewed distributions. Indeed, the use of skewness tests to discriminate between these distributions lacks theoretical foundation. The performance of skewness tests is shown to be very sensitive to the kurtosis of the underlying distribution.",
keywords = "kurtosis, multivariate, normality, radii, skewness, univariate normality",
author = "Horswell, {Ronald L.} and Looney, {Stephen Warwick}",
year = "1993",
month = "1",
day = "1",
doi = "10.1080/03610919308813102",
language = "English (US)",
volume = "22",
pages = "437--459",
journal = "Communications in Statistics: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Diagnostic limitations of skewness coefficients in assessing departures from univariate and multivariate normality

AU - Horswell, Ronald L.

AU - Looney, Stephen Warwick

PY - 1993/1/1

Y1 - 1993/1/1

N2 - While many tests of univariate and multivariate normality have been proposed, those based on skewness and kurtosis coefficients are widely presumed to offer the advantage of diagnosing how distributions depart from normality. However, results summarized from many Monte Carlo studies show that tests based on skewness coefficients do not reliably discriminate between skewed and non-skewed distributions. Indeed, the use of skewness tests to discriminate between these distributions lacks theoretical foundation. The performance of skewness tests is shown to be very sensitive to the kurtosis of the underlying distribution.

AB - While many tests of univariate and multivariate normality have been proposed, those based on skewness and kurtosis coefficients are widely presumed to offer the advantage of diagnosing how distributions depart from normality. However, results summarized from many Monte Carlo studies show that tests based on skewness coefficients do not reliably discriminate between skewed and non-skewed distributions. Indeed, the use of skewness tests to discriminate between these distributions lacks theoretical foundation. The performance of skewness tests is shown to be very sensitive to the kurtosis of the underlying distribution.

KW - kurtosis

KW - multivariate

KW - normality

KW - radii

KW - skewness

KW - univariate normality

UR - http://www.scopus.com/inward/record.url?scp=0011557931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0011557931&partnerID=8YFLogxK

U2 - 10.1080/03610919308813102

DO - 10.1080/03610919308813102

M3 - Article

AN - SCOPUS:0011557931

VL - 22

SP - 437

EP - 459

JO - Communications in Statistics: Simulation and Computation

JF - Communications in Statistics: Simulation and Computation

SN - 0361-0918

IS - 2

ER -