Approximate sample size formulas for testing group mean differences when variances are unequal in one-way ANOVA

Jiin Huarng Guo, Wei-Ming Luh

研究成果: Article

6 引文 (Scopus)

摘要

This study proposes an approach for determining appropriate sample size for Welch's F test when unequal variances are expected. Given a certain maximum deviation in population means and using the quantile of F and t distributions, there is no need to specify a noncentrality parameter and it is easy to estimate the approximate sample size needed for heterogeneous one-way ANOVA. The theoretical results are validated by a comparison to the results from a Monte Carlo simulation. Simulation results for the empirical power indicate that the sample size needed by the proposed formulas can almost always achieve the desired power level when Welch's F test is applied to data that are conditionally nonnormal and heterogeneous. Two illustrative examples of the use of the proposed procedure are given to calculate balanced and optimal sample sizes, respectively. Moreover, three sample size tables for two-, four-, and six-group problems are provided, respectively, for practitioners.

原文English
頁(從 - 到)959-971
頁數13
期刊Educational and Psychological Measurement
68
發行號6
DOIs
出版狀態Published - 2008 一月 1

指紋

Group Testing
Analysis of variance (ANOVA)
Unequal
Sample Size
Analysis of Variance
Testing
F Test
Group
Noncentrality Parameter
problem group
F distribution
simulation
t-distribution
Quantile
Tables
Deviation
Monte Carlo Simulation
Monte Carlo simulation
Calculate
Estimate

All Science Journal Classification (ASJC) codes

  • Education
  • Developmental and Educational Psychology
  • Applied Psychology
  • Applied Mathematics

引用此文

@article{475b7acd20744f578df990b0c1d17996,
title = "Approximate sample size formulas for testing group mean differences when variances are unequal in one-way ANOVA",
abstract = "This study proposes an approach for determining appropriate sample size for Welch's F test when unequal variances are expected. Given a certain maximum deviation in population means and using the quantile of F and t distributions, there is no need to specify a noncentrality parameter and it is easy to estimate the approximate sample size needed for heterogeneous one-way ANOVA. The theoretical results are validated by a comparison to the results from a Monte Carlo simulation. Simulation results for the empirical power indicate that the sample size needed by the proposed formulas can almost always achieve the desired power level when Welch's F test is applied to data that are conditionally nonnormal and heterogeneous. Two illustrative examples of the use of the proposed procedure are given to calculate balanced and optimal sample sizes, respectively. Moreover, three sample size tables for two-, four-, and six-group problems are provided, respectively, for practitioners.",
author = "Guo, {Jiin Huarng} and Wei-Ming Luh",
year = "2008",
month = "1",
day = "1",
doi = "10.1177/0013164408318759",
language = "English",
volume = "68",
pages = "959--971",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "6",

}

TY - JOUR

T1 - Approximate sample size formulas for testing group mean differences when variances are unequal in one-way ANOVA

AU - Guo, Jiin Huarng

AU - Luh, Wei-Ming

PY - 2008/1/1

Y1 - 2008/1/1

N2 - This study proposes an approach for determining appropriate sample size for Welch's F test when unequal variances are expected. Given a certain maximum deviation in population means and using the quantile of F and t distributions, there is no need to specify a noncentrality parameter and it is easy to estimate the approximate sample size needed for heterogeneous one-way ANOVA. The theoretical results are validated by a comparison to the results from a Monte Carlo simulation. Simulation results for the empirical power indicate that the sample size needed by the proposed formulas can almost always achieve the desired power level when Welch's F test is applied to data that are conditionally nonnormal and heterogeneous. Two illustrative examples of the use of the proposed procedure are given to calculate balanced and optimal sample sizes, respectively. Moreover, three sample size tables for two-, four-, and six-group problems are provided, respectively, for practitioners.

AB - This study proposes an approach for determining appropriate sample size for Welch's F test when unequal variances are expected. Given a certain maximum deviation in population means and using the quantile of F and t distributions, there is no need to specify a noncentrality parameter and it is easy to estimate the approximate sample size needed for heterogeneous one-way ANOVA. The theoretical results are validated by a comparison to the results from a Monte Carlo simulation. Simulation results for the empirical power indicate that the sample size needed by the proposed formulas can almost always achieve the desired power level when Welch's F test is applied to data that are conditionally nonnormal and heterogeneous. Two illustrative examples of the use of the proposed procedure are given to calculate balanced and optimal sample sizes, respectively. Moreover, three sample size tables for two-, four-, and six-group problems are provided, respectively, for practitioners.

UR - http://www.scopus.com/inward/record.url?scp=56749151318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56749151318&partnerID=8YFLogxK

U2 - 10.1177/0013164408318759

DO - 10.1177/0013164408318759

M3 - Article

AN - SCOPUS:56749151318

VL - 68

SP - 959

EP - 971

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 6

ER -