New heterogeneous test statistics for the unbalanced fixed-effect nested design

Jiin Huarng Guo, L. Billard, Wei-Ming Luh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

When the underlying variances are unknown or/and unequal, using the conventional F test is problematic in the two-factor hierarchical data structure. Prompted by the approximate test statistics (Welch and Alexander-Govern methods), the authors develop four new heterogeneous test statistics to test factor A and factor B nested within A for the unbalanced fixed-effect two-stage nested design under variance heterogeneity. The actual significance levels and statistical power of the test statistics were compared in a simulation study. The results show that the proposed procedures maintain better Type I error rate control and have greater statistical power than those obtained by the conventional F test in various conditions. Therefore, the proposed test statistics are recommended in terms of robustness and easy implementation.

Original languageEnglish
Pages (from-to)259-276
Number of pages18
JournalBritish Journal of Mathematical and Statistical Psychology
Volume64
Issue number2
DOIs
Publication statusPublished - 2011 May 1

Fingerprint

Nested Design
Fixed Effects
Test Statistic
Statistical Power
F Test
Variance Heterogeneity
Two-stage Design
Hierarchical Data
Type I Error Rate
Rate Control
Significance level
Error Control
Hierarchical Structure
Unequal
Data Structures
Simulation Study
Robustness
Unknown
Statistics

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Arts and Humanities (miscellaneous)
  • Psychology(all)

Cite this

@article{90892d4c721a4586afd44da76c490ec0,
title = "New heterogeneous test statistics for the unbalanced fixed-effect nested design",
abstract = "When the underlying variances are unknown or/and unequal, using the conventional F test is problematic in the two-factor hierarchical data structure. Prompted by the approximate test statistics (Welch and Alexander-Govern methods), the authors develop four new heterogeneous test statistics to test factor A and factor B nested within A for the unbalanced fixed-effect two-stage nested design under variance heterogeneity. The actual significance levels and statistical power of the test statistics were compared in a simulation study. The results show that the proposed procedures maintain better Type I error rate control and have greater statistical power than those obtained by the conventional F test in various conditions. Therefore, the proposed test statistics are recommended in terms of robustness and easy implementation.",
author = "Guo, {Jiin Huarng} and L. Billard and Wei-Ming Luh",
year = "2011",
month = "5",
day = "1",
doi = "10.1348/000711010X512688",
language = "English",
volume = "64",
pages = "259--276",
journal = "British Journal of Mathematical and Statistical Psychology",
issn = "0007-1102",
publisher = "Wiley-Blackwell",
number = "2",

}

New heterogeneous test statistics for the unbalanced fixed-effect nested design. / Guo, Jiin Huarng; Billard, L.; Luh, Wei-Ming.

In: British Journal of Mathematical and Statistical Psychology, Vol. 64, No. 2, 01.05.2011, p. 259-276.

Research output: Contribution to journalArticle

TY - JOUR

T1 - New heterogeneous test statistics for the unbalanced fixed-effect nested design

AU - Guo, Jiin Huarng

AU - Billard, L.

AU - Luh, Wei-Ming

PY - 2011/5/1

Y1 - 2011/5/1

N2 - When the underlying variances are unknown or/and unequal, using the conventional F test is problematic in the two-factor hierarchical data structure. Prompted by the approximate test statistics (Welch and Alexander-Govern methods), the authors develop four new heterogeneous test statistics to test factor A and factor B nested within A for the unbalanced fixed-effect two-stage nested design under variance heterogeneity. The actual significance levels and statistical power of the test statistics were compared in a simulation study. The results show that the proposed procedures maintain better Type I error rate control and have greater statistical power than those obtained by the conventional F test in various conditions. Therefore, the proposed test statistics are recommended in terms of robustness and easy implementation.

AB - When the underlying variances are unknown or/and unequal, using the conventional F test is problematic in the two-factor hierarchical data structure. Prompted by the approximate test statistics (Welch and Alexander-Govern methods), the authors develop four new heterogeneous test statistics to test factor A and factor B nested within A for the unbalanced fixed-effect two-stage nested design under variance heterogeneity. The actual significance levels and statistical power of the test statistics were compared in a simulation study. The results show that the proposed procedures maintain better Type I error rate control and have greater statistical power than those obtained by the conventional F test in various conditions. Therefore, the proposed test statistics are recommended in terms of robustness and easy implementation.

UR - http://www.scopus.com/inward/record.url?scp=79954588051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954588051&partnerID=8YFLogxK

U2 - 10.1348/000711010X512688

DO - 10.1348/000711010X512688

M3 - Article

C2 - 21492132

AN - SCOPUS:79954588051

VL - 64

SP - 259

EP - 276

JO - British Journal of Mathematical and Statistical Psychology

JF - British Journal of Mathematical and Statistical Psychology

SN - 0007-1102

IS - 2

ER -