A cautionary note on the use of information fit indexes in covariance structure modeling with means

J.M. Wicherts, C.V. Dolan

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Information fit indexes such as Akaike Information Criterion, Consistent Akaike Information Criterion, Bayesian Information Criterion, and the expected cross validation index can be valuable in assessing the relative fit of structural equation models that differ regarding restrictiveness. In cases in which models without mean restrictions (i.e., saturated mean structure) are compared to models with restricted (i.e., modeled) means, one should take account of the presence of means, even if the model is saturated with respect to the means. The failure to do this can result in an incorrect rank order of models in terms of the information fit indexes. We demonstrate this point by an analysis of measurement invariance in a multigroup confirmatory factor model.
Original languageEnglish
Pages (from-to)45-50
Number of pages6
JournalStructural Equation Modeling
Volume11
DOIs
Publication statusPublished - 2004
Externally publishedYes

Fingerprint

Covariance Structure
Modeling
Akaike Information Criterion
Measurement Invariance
Rank order
Bayesian Information Criterion
Structural Equation Model
Factor Models
structural model
Cross-validation
Model
Invariance
Restriction
Demonstrate
Akaike information criterion

Cite this

@article{f43d0569a4cb48b89d2a66efff21a645,
title = "A cautionary note on the use of information fit indexes in covariance structure modeling with means",
abstract = "Information fit indexes such as Akaike Information Criterion, Consistent Akaike Information Criterion, Bayesian Information Criterion, and the expected cross validation index can be valuable in assessing the relative fit of structural equation models that differ regarding restrictiveness. In cases in which models without mean restrictions (i.e., saturated mean structure) are compared to models with restricted (i.e., modeled) means, one should take account of the presence of means, even if the model is saturated with respect to the means. The failure to do this can result in an incorrect rank order of models in terms of the information fit indexes. We demonstrate this point by an analysis of measurement invariance in a multigroup confirmatory factor model.",
author = "J.M. Wicherts and C.V. Dolan",
year = "2004",
doi = "10.1207/S15328007SEM1101_3",
language = "English",
volume = "11",
pages = "45--50",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD",

}

A cautionary note on the use of information fit indexes in covariance structure modeling with means. / Wicherts, J.M.; Dolan, C.V.

In: Structural Equation Modeling, Vol. 11, 2004, p. 45-50.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - A cautionary note on the use of information fit indexes in covariance structure modeling with means

AU - Wicherts, J.M.

AU - Dolan, C.V.

PY - 2004

Y1 - 2004

N2 - Information fit indexes such as Akaike Information Criterion, Consistent Akaike Information Criterion, Bayesian Information Criterion, and the expected cross validation index can be valuable in assessing the relative fit of structural equation models that differ regarding restrictiveness. In cases in which models without mean restrictions (i.e., saturated mean structure) are compared to models with restricted (i.e., modeled) means, one should take account of the presence of means, even if the model is saturated with respect to the means. The failure to do this can result in an incorrect rank order of models in terms of the information fit indexes. We demonstrate this point by an analysis of measurement invariance in a multigroup confirmatory factor model.

AB - Information fit indexes such as Akaike Information Criterion, Consistent Akaike Information Criterion, Bayesian Information Criterion, and the expected cross validation index can be valuable in assessing the relative fit of structural equation models that differ regarding restrictiveness. In cases in which models without mean restrictions (i.e., saturated mean structure) are compared to models with restricted (i.e., modeled) means, one should take account of the presence of means, even if the model is saturated with respect to the means. The failure to do this can result in an incorrect rank order of models in terms of the information fit indexes. We demonstrate this point by an analysis of measurement invariance in a multigroup confirmatory factor model.

U2 - 10.1207/S15328007SEM1101_3

DO - 10.1207/S15328007SEM1101_3

M3 - Article

VL - 11

SP - 45

EP - 50

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

ER -