An investigation of the rank transform in the multivariate one-sample location problem

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In the multivariate one-sample location problem, the size of Hotelling's T2 test fluctuates widely from nominal alpha as the distributions deviate from multinormality due to skewness or the distributions have tails heavier than multinormal distributions. For skewed distributions, several modifications of Hotelling's T2 are available to adjust for skewness. In this paper for symmetric distributions, a test statistic based on the signed ranks of the data is discussed and investigated. The proposed test statistic is obtained by computing Hotelling's T2 statistic as a function of the signed ranks and is equivalent to a statistic of Puri and Sen (1971). An approximation to its null distribution is derived by moment matching criterion. Monte Carlo results are presented to compare several test statistics. For various multidimensional distributions the Monte Carlo results indicate the robustness of the proposed statistics. For bivariate normal, uniform and Cauchy distributions, the results of a power comparison study are summarized.

Original languageEnglish
Pages (from-to)139-155
Number of pages17
JournalJournal of Statistical Computation and Simulation
Volume16
Issue number2
DOIs
StatePublished - Dec 1 1982
Externally publishedYes

Fingerprint

Location Problem
Hotelling's T2
Statistics
Transform
Test Statistic
Skewness
Signed
Statistic
Moment Matching
Power Comparison
Bivariate Normal Distribution
Cauchy Distribution
Skewed Distribution
Heavy Tails
Symmetric Distributions
Null Distribution
Uniform distribution
Categorical or nominal
Robustness
Location problem

All Science Journal Classification (ASJC) codes

  • Statistics, Probability and Uncertainty
  • Modeling and Simulation
  • Statistics and Probability
  • Applied Mathematics

Cite this

An investigation of the rank transform in the multivariate one-sample location problem. / Nath, Ravinder.

In: Journal of Statistical Computation and Simulation, Vol. 16, No. 2, 01.12.1982, p. 139-155.

Research output: Contribution to journalArticle

@article{b9437acc4c7e44fe9935989b325658ec,
title = "An investigation of the rank transform in the multivariate one-sample location problem",
abstract = "In the multivariate one-sample location problem, the size of Hotelling's T2 test fluctuates widely from nominal alpha as the distributions deviate from multinormality due to skewness or the distributions have tails heavier than multinormal distributions. For skewed distributions, several modifications of Hotelling's T2 are available to adjust for skewness. In this paper for symmetric distributions, a test statistic based on the signed ranks of the data is discussed and investigated. The proposed test statistic is obtained by computing Hotelling's T2 statistic as a function of the signed ranks and is equivalent to a statistic of Puri and Sen (1971). An approximation to its null distribution is derived by moment matching criterion. Monte Carlo results are presented to compare several test statistics. For various multidimensional distributions the Monte Carlo results indicate the robustness of the proposed statistics. For bivariate normal, uniform and Cauchy distributions, the results of a power comparison study are summarized.",
author = "Ravinder Nath",
year = "1982",
month = "12",
day = "1",
doi = "10.1080/00949658208810616",
language = "English",
volume = "16",
pages = "139--155",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - An investigation of the rank transform in the multivariate one-sample location problem

AU - Nath, Ravinder

PY - 1982/12/1

Y1 - 1982/12/1

N2 - In the multivariate one-sample location problem, the size of Hotelling's T2 test fluctuates widely from nominal alpha as the distributions deviate from multinormality due to skewness or the distributions have tails heavier than multinormal distributions. For skewed distributions, several modifications of Hotelling's T2 are available to adjust for skewness. In this paper for symmetric distributions, a test statistic based on the signed ranks of the data is discussed and investigated. The proposed test statistic is obtained by computing Hotelling's T2 statistic as a function of the signed ranks and is equivalent to a statistic of Puri and Sen (1971). An approximation to its null distribution is derived by moment matching criterion. Monte Carlo results are presented to compare several test statistics. For various multidimensional distributions the Monte Carlo results indicate the robustness of the proposed statistics. For bivariate normal, uniform and Cauchy distributions, the results of a power comparison study are summarized.

AB - In the multivariate one-sample location problem, the size of Hotelling's T2 test fluctuates widely from nominal alpha as the distributions deviate from multinormality due to skewness or the distributions have tails heavier than multinormal distributions. For skewed distributions, several modifications of Hotelling's T2 are available to adjust for skewness. In this paper for symmetric distributions, a test statistic based on the signed ranks of the data is discussed and investigated. The proposed test statistic is obtained by computing Hotelling's T2 statistic as a function of the signed ranks and is equivalent to a statistic of Puri and Sen (1971). An approximation to its null distribution is derived by moment matching criterion. Monte Carlo results are presented to compare several test statistics. For various multidimensional distributions the Monte Carlo results indicate the robustness of the proposed statistics. For bivariate normal, uniform and Cauchy distributions, the results of a power comparison study are summarized.

UR - http://www.scopus.com/inward/record.url?scp=0345633906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0345633906&partnerID=8YFLogxK

U2 - 10.1080/00949658208810616

DO - 10.1080/00949658208810616

M3 - Article

VL - 16

SP - 139

EP - 155

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 2

ER -