The effect of design imbalance on the power of the F-test of a variance component in the one-way random model

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The ANOVA-based F-test used for testing the significance of the random effect variance component is a valid test for an unbalanced one-way random model. However, it does not have an uniform optimum property. For example, this test is not uniformly most powerful invariant (UMPI). In fact, there is no UMPI test in the unbalanced case (see KHURI, MATHEW, and SINHA, 1998). The power of the F-test depends not only on the design used, but also on the true values of the variance components. As KHURI (1996) noted, we can gain a better insight into the effect of data imbalance on the power of the F-test using a method for modelling the power in terms of the design parameters and the variance components. In this study, generalized linear modelling (GLM) techniques are used for this purpose. It is shown that GLM, in combination with a method of generating designs with a specified degree of imbalance, is an effective way of studying the behavior of the power of the F-test in a one-way random model.

Original languageEnglish
Pages (from-to)238-248
Number of pages11
JournalBiometrical Journal
Volume45
Issue number2
DOIs
Publication statusPublished - 2003 Jan 1

Fingerprint

F Test
Variance Components
Modeling
Invariant
Random Effects
Parameter Design
Model
Valid
Testing
Design
Imbalance
Variance components

Keywords

  • Analysis of Variance
  • Generalized Linear Models
  • Measure of Imbalance
  • One-way Random Model
  • Power
  • Unbalanced Data

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

The effect of design imbalance on the power of the F-test of a variance component in the one-way random model. / Lee, Juneyoung.

In: Biometrical Journal, Vol. 45, No. 2, 01.01.2003, p. 238-248.

Research output: Contribution to journalArticle

@article{d1d33d49e6624ff2a15deb8a307ddfd1,
title = "The effect of design imbalance on the power of the F-test of a variance component in the one-way random model",
abstract = "The ANOVA-based F-test used for testing the significance of the random effect variance component is a valid test for an unbalanced one-way random model. However, it does not have an uniform optimum property. For example, this test is not uniformly most powerful invariant (UMPI). In fact, there is no UMPI test in the unbalanced case (see KHURI, MATHEW, and SINHA, 1998). The power of the F-test depends not only on the design used, but also on the true values of the variance components. As KHURI (1996) noted, we can gain a better insight into the effect of data imbalance on the power of the F-test using a method for modelling the power in terms of the design parameters and the variance components. In this study, generalized linear modelling (GLM) techniques are used for this purpose. It is shown that GLM, in combination with a method of generating designs with a specified degree of imbalance, is an effective way of studying the behavior of the power of the F-test in a one-way random model.",
keywords = "Analysis of Variance, Generalized Linear Models, Measure of Imbalance, One-way Random Model, Power, Unbalanced Data",
author = "Juneyoung Lee",
year = "2003",
month = "1",
day = "1",
doi = "10.1002/bimj.200390009",
language = "English",
volume = "45",
pages = "238--248",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "2",

}

TY - JOUR

T1 - The effect of design imbalance on the power of the F-test of a variance component in the one-way random model

AU - Lee, Juneyoung

PY - 2003/1/1

Y1 - 2003/1/1

N2 - The ANOVA-based F-test used for testing the significance of the random effect variance component is a valid test for an unbalanced one-way random model. However, it does not have an uniform optimum property. For example, this test is not uniformly most powerful invariant (UMPI). In fact, there is no UMPI test in the unbalanced case (see KHURI, MATHEW, and SINHA, 1998). The power of the F-test depends not only on the design used, but also on the true values of the variance components. As KHURI (1996) noted, we can gain a better insight into the effect of data imbalance on the power of the F-test using a method for modelling the power in terms of the design parameters and the variance components. In this study, generalized linear modelling (GLM) techniques are used for this purpose. It is shown that GLM, in combination with a method of generating designs with a specified degree of imbalance, is an effective way of studying the behavior of the power of the F-test in a one-way random model.

AB - The ANOVA-based F-test used for testing the significance of the random effect variance component is a valid test for an unbalanced one-way random model. However, it does not have an uniform optimum property. For example, this test is not uniformly most powerful invariant (UMPI). In fact, there is no UMPI test in the unbalanced case (see KHURI, MATHEW, and SINHA, 1998). The power of the F-test depends not only on the design used, but also on the true values of the variance components. As KHURI (1996) noted, we can gain a better insight into the effect of data imbalance on the power of the F-test using a method for modelling the power in terms of the design parameters and the variance components. In this study, generalized linear modelling (GLM) techniques are used for this purpose. It is shown that GLM, in combination with a method of generating designs with a specified degree of imbalance, is an effective way of studying the behavior of the power of the F-test in a one-way random model.

KW - Analysis of Variance

KW - Generalized Linear Models

KW - Measure of Imbalance

KW - One-way Random Model

KW - Power

KW - Unbalanced Data

UR - http://www.scopus.com/inward/record.url?scp=0037251666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037251666&partnerID=8YFLogxK

U2 - 10.1002/bimj.200390009

DO - 10.1002/bimj.200390009

M3 - Article

AN - SCOPUS:0037251666

VL - 45

SP - 238

EP - 248

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 2

ER -