Goodness of fit in confirmatory factor analysis: The effects of sample size and model parsimony

Quality & Quantity

Volumn 28, Issue 2, 1994, Pages 185-217

  Marsh, Herbert W ^a   Balla, John ^b  

^a UNIVERSITY OF WESTERN SYDNEY   (Australia)

^b UNIVERSITY OF SYDNEY   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 21344475673     PISSN: 00335177     EISSN: 15737845     Source Type: Journal    
DOI: 10.1007/BF01102761     Document Type: Article

References (27)

1. A new look at the statistical model identification
2. Comparative fit indices in structural models
3. Significance tests and goodness of fit in the analysis of covariance structures
4. Sample size and Bentler and Bonett's nonnormed fit index
5. Overall fit in covariance structure models: Two types of sample size effects
6. Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions
7. Generalized least squares estimators in the analysis of covariance structures
8. Single sample cross-validation indices for covariance structures
9. Cross-validation of covariance structures
10. Model selection in covariance structures analysis and the “problem” of sample size: A clarification
11. The analysis of covariance structures: Goodness-of-fit indices
12. The factorial invariance of responses by males and females to a multidimensional self-concept instrument: Substantive and methodological issues
13. Goodness-of-fit indices in confirmatory factor analysis: The effect of sample size
14. Choosing a multivariate model: Noncentrality and goodness-of-fit
15. An index of Goodness-of-fit based on noncentrality
16. Evaluation of goodness-of-flt indices for structural equation models
17. Estimating the dimension of a model
18. Structure model evaluation and modification: An interval estimation approach
19. A fit index for covariance structure models under arbitrary GLS estimation
20. The reliability coefficient for maximum likelihood factor analysis
21. Tests of statistical hypotheses concening several parameters when the number of observations is large