The effect of sampling error on convergence, improper solutions, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis

James C. Anderson; David W. Gerbing

doi:10.1007/BF02294170

The effect of sampling error on convergence, improper solutions, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis

James C. Anderson^*, David W. Gerbing

^*Corresponding author for this work

Marketing

Research output: Contribution to journal › Article › peer-review

1039 Scopus citations

Abstract

A Monte Carlo study assessed the effect of sampling error and model characteristics on the occurrence of nonconvergent solutions, improper solutions and the distribution of goodness-of-fit indices in maximum likelihood confirmatory factor analysis. Nonconvergent and improper solutions occurred more frequently for smaller sample sizes and for models with fewer indicators of each factor. Effects of practical significance due to sample size, the number of indicators per factor and the number of factors were found for GFI, AGFI, and RMR, whereas no practical effects were found for the probability values associated with the chi-square likelihood ratio test.

Original language	English (US)
Pages (from-to)	155-173
Number of pages	19
Journal	Psychometrika
Volume	49
Issue number	2
DOIs	https://doi.org/10.1007/BF02294170
State	Published - Jun 1984

Keywords

Confirmatory factory analysis
LISREL
Maximum likelihood
Monte Carlo

ASJC Scopus subject areas

Psychology(all)
Applied Mathematics

Access to Document

10.1007/BF02294170

Cite this

@article{7d7790a295cd4cdc8186cc027b6c4b21,

title = "The effect of sampling error on convergence, improper solutions, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis",

abstract = "A Monte Carlo study assessed the effect of sampling error and model characteristics on the occurrence of nonconvergent solutions, improper solutions and the distribution of goodness-of-fit indices in maximum likelihood confirmatory factor analysis. Nonconvergent and improper solutions occurred more frequently for smaller sample sizes and for models with fewer indicators of each factor. Effects of practical significance due to sample size, the number of indicators per factor and the number of factors were found for GFI, AGFI, and RMR, whereas no practical effects were found for the probability values associated with the chi-square likelihood ratio test.",

keywords = "Confirmatory factory analysis, LISREL, Maximum likelihood, Monte Carlo",

author = "Anderson, {James C.} and Gerbing, {David W.}",

year = "1984",

month = jun,

doi = "10.1007/BF02294170",

language = "English (US)",

volume = "49",

pages = "155--173",

journal = "Psychometrika",

issn = "0033-3123",

publisher = "Springer New York",

number = "2",

}

TY - JOUR

T1 - The effect of sampling error on convergence, improper solutions, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis

AU - Anderson, James C.

AU - Gerbing, David W.

PY - 1984/6

Y1 - 1984/6

N2 - A Monte Carlo study assessed the effect of sampling error and model characteristics on the occurrence of nonconvergent solutions, improper solutions and the distribution of goodness-of-fit indices in maximum likelihood confirmatory factor analysis. Nonconvergent and improper solutions occurred more frequently for smaller sample sizes and for models with fewer indicators of each factor. Effects of practical significance due to sample size, the number of indicators per factor and the number of factors were found for GFI, AGFI, and RMR, whereas no practical effects were found for the probability values associated with the chi-square likelihood ratio test.

AB - A Monte Carlo study assessed the effect of sampling error and model characteristics on the occurrence of nonconvergent solutions, improper solutions and the distribution of goodness-of-fit indices in maximum likelihood confirmatory factor analysis. Nonconvergent and improper solutions occurred more frequently for smaller sample sizes and for models with fewer indicators of each factor. Effects of practical significance due to sample size, the number of indicators per factor and the number of factors were found for GFI, AGFI, and RMR, whereas no practical effects were found for the probability values associated with the chi-square likelihood ratio test.

KW - Confirmatory factory analysis

KW - LISREL

KW - Maximum likelihood

KW - Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=34147096911&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147096911&partnerID=8YFLogxK

U2 - 10.1007/BF02294170

DO - 10.1007/BF02294170

M3 - Article

AN - SCOPUS:34147096911

SN - 0033-3123

VL - 49

SP - 155

EP - 173

JO - Psychometrika

JF - Psychometrika

IS - 2

ER -

The effect of sampling error on convergence, improper solutions, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this