The Effectiveness of Methods for Analyzing Multivariate Factorial Data

Robert A. McDonald, Charles F. Seifert, Steven J. Lorenzet, Susan Givens, James Jaccard

Research output: Contribution to journalArticle

Abstract

A Monte Carlo simulation was used to examine the effectiveness of univariate analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), and multiple indicator structural equation (AUSE) modeling to analyze data from multivariate factorial designs. The MISE method yielded downwardly biased standard errors for the univariate parameter estimates in the small sample size conditions. In the large sample size data conditions, the MISE method outperformed MANOVA and ANOVA when the covariate accounted for variation in the dependent variable and variables were unreliable. With multivariate statistical tests, MANOVA outperformed the MISE method in the Type I error conditions and the MISE method outperfonned MANOVA in the Type II error conditions. The Bonferroni methods were overly conservative in controlling Type I error rates for univariate tests, but a modified Bonferroni method had higher statistical power than the Bonferroni method. Both the Bonferroni and modified methods adequately controlled multivariate Type I error rates.

Original languageEnglish (US)
Pages (from-to)255-274
Number of pages20
JournalOrganizational Research Methods
Volume5
Issue number3
DOIs
StatePublished - 2002

Fingerprint

Analysis of variance (ANOVA)
Statistical tests
Multivariate Analysis
Multivariate analysis of variance
Type I error

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Strategy and Management
  • Management of Technology and Innovation

Cite this

The Effectiveness of Methods for Analyzing Multivariate Factorial Data. / McDonald, Robert A.; Seifert, Charles F.; Lorenzet, Steven J.; Givens, Susan; Jaccard, James.

In: Organizational Research Methods, Vol. 5, No. 3, 2002, p. 255-274.

Research output: Contribution to journalArticle

McDonald, Robert A. ; Seifert, Charles F. ; Lorenzet, Steven J. ; Givens, Susan ; Jaccard, James. / The Effectiveness of Methods for Analyzing Multivariate Factorial Data. In: Organizational Research Methods. 2002 ; Vol. 5, No. 3. pp. 255-274.
@article{5efeb2e2fe5c4489a83bdac8cf1b8619,
title = "The Effectiveness of Methods for Analyzing Multivariate Factorial Data",
abstract = "A Monte Carlo simulation was used to examine the effectiveness of univariate analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), and multiple indicator structural equation (AUSE) modeling to analyze data from multivariate factorial designs. The MISE method yielded downwardly biased standard errors for the univariate parameter estimates in the small sample size conditions. In the large sample size data conditions, the MISE method outperformed MANOVA and ANOVA when the covariate accounted for variation in the dependent variable and variables were unreliable. With multivariate statistical tests, MANOVA outperformed the MISE method in the Type I error conditions and the MISE method outperfonned MANOVA in the Type II error conditions. The Bonferroni methods were overly conservative in controlling Type I error rates for univariate tests, but a modified Bonferroni method had higher statistical power than the Bonferroni method. Both the Bonferroni and modified methods adequately controlled multivariate Type I error rates.",
author = "McDonald, {Robert A.} and Seifert, {Charles F.} and Lorenzet, {Steven J.} and Susan Givens and James Jaccard",
year = "2002",
doi = "10.1177/1094428102005003004",
language = "English (US)",
volume = "5",
pages = "255--274",
journal = "Organizational Research Methods",
issn = "1094-4281",
publisher = "SAGE Publications Inc.",
number = "3",

}

TY - JOUR

T1 - The Effectiveness of Methods for Analyzing Multivariate Factorial Data

AU - McDonald, Robert A.

AU - Seifert, Charles F.

AU - Lorenzet, Steven J.

AU - Givens, Susan

AU - Jaccard, James

PY - 2002

Y1 - 2002

N2 - A Monte Carlo simulation was used to examine the effectiveness of univariate analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), and multiple indicator structural equation (AUSE) modeling to analyze data from multivariate factorial designs. The MISE method yielded downwardly biased standard errors for the univariate parameter estimates in the small sample size conditions. In the large sample size data conditions, the MISE method outperformed MANOVA and ANOVA when the covariate accounted for variation in the dependent variable and variables were unreliable. With multivariate statistical tests, MANOVA outperformed the MISE method in the Type I error conditions and the MISE method outperfonned MANOVA in the Type II error conditions. The Bonferroni methods were overly conservative in controlling Type I error rates for univariate tests, but a modified Bonferroni method had higher statistical power than the Bonferroni method. Both the Bonferroni and modified methods adequately controlled multivariate Type I error rates.

AB - A Monte Carlo simulation was used to examine the effectiveness of univariate analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), and multiple indicator structural equation (AUSE) modeling to analyze data from multivariate factorial designs. The MISE method yielded downwardly biased standard errors for the univariate parameter estimates in the small sample size conditions. In the large sample size data conditions, the MISE method outperformed MANOVA and ANOVA when the covariate accounted for variation in the dependent variable and variables were unreliable. With multivariate statistical tests, MANOVA outperformed the MISE method in the Type I error conditions and the MISE method outperfonned MANOVA in the Type II error conditions. The Bonferroni methods were overly conservative in controlling Type I error rates for univariate tests, but a modified Bonferroni method had higher statistical power than the Bonferroni method. Both the Bonferroni and modified methods adequately controlled multivariate Type I error rates.

UR - http://www.scopus.com/inward/record.url?scp=85018194972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018194972&partnerID=8YFLogxK

U2 - 10.1177/1094428102005003004

DO - 10.1177/1094428102005003004

M3 - Article

VL - 5

SP - 255

EP - 274

JO - Organizational Research Methods

JF - Organizational Research Methods

SN - 1094-4281

IS - 3

ER -