A Monte Carlo Comparison of Some t-Tests

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A class of statistical tests for testing the hypothesis Ho: Δ = 0, where Δ is a location parameter, is proposed. The test statistic is defined in terms of the signed ranks of the sample data. It is shown, by the method of moment matching, that under the null hypothesis test statistics in the proposed class have approximately a i-distribution. A Monte Carlo simulation study is presented inorder to compare the significance levels and Power of these tests with numerous other tests.

Original languageEnglish
Pages (from-to)235-260
Number of pages26
JournalJournal of Statistical Computation and Simulation
Volume20
Issue number3
DOIs
StatePublished - 1984
Externally publishedYes

Fingerprint

t-test
Test Statistic
Statistics
Moment Matching
Power of Test
Significance level
Statistical tests
Location Parameter
Hypothesis Test
Method of Moments
Statistical test
Method of moments
Signed
Null hypothesis
Monte Carlo Simulation
Simulation Study
Testing
Class
T-test
Test statistic

All Science Journal Classification (ASJC) codes

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

Cite this

A Monte Carlo Comparison of Some t-Tests. / Nath, Ravinder.

In: Journal of Statistical Computation and Simulation, Vol. 20, No. 3, 1984, p. 235-260.

Research output: Contribution to journalArticle

@article{7399b363002940fc8577dc6a42b72b5e,
title = "A Monte Carlo Comparison of Some t-Tests",
abstract = "A class of statistical tests for testing the hypothesis Ho: Δ = 0, where Δ is a location parameter, is proposed. The test statistic is defined in terms of the signed ranks of the sample data. It is shown, by the method of moment matching, that under the null hypothesis test statistics in the proposed class have approximately a i-distribution. A Monte Carlo simulation study is presented inorder to compare the significance levels and Power of these tests with numerous other tests.",
author = "Ravinder Nath",
year = "1984",
doi = "10.1080/00949658408810779",
language = "English",
volume = "20",
pages = "235--260",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - A Monte Carlo Comparison of Some t-Tests

AU - Nath, Ravinder

PY - 1984

Y1 - 1984

N2 - A class of statistical tests for testing the hypothesis Ho: Δ = 0, where Δ is a location parameter, is proposed. The test statistic is defined in terms of the signed ranks of the sample data. It is shown, by the method of moment matching, that under the null hypothesis test statistics in the proposed class have approximately a i-distribution. A Monte Carlo simulation study is presented inorder to compare the significance levels and Power of these tests with numerous other tests.

AB - A class of statistical tests for testing the hypothesis Ho: Δ = 0, where Δ is a location parameter, is proposed. The test statistic is defined in terms of the signed ranks of the sample data. It is shown, by the method of moment matching, that under the null hypothesis test statistics in the proposed class have approximately a i-distribution. A Monte Carlo simulation study is presented inorder to compare the significance levels and Power of these tests with numerous other tests.

UR - http://www.scopus.com/inward/record.url?scp=84947690520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947690520&partnerID=8YFLogxK

U2 - 10.1080/00949658408810779

DO - 10.1080/00949658408810779

M3 - Article

VL - 20

SP - 235

EP - 260

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 3

ER -