Comparer des méthodes

	Oméga ordinal de McDonald	Analyse Factorielle Confirmatoire (AFC)
Domaine	Psychométrie	Psychométrie
Famille	Latent structure	Latent structure
Année d'origine	2007	1969
Auteur d'origine	Bruno D. Zumbo, Anne M. Gadermann, and Cornelia Zeisser (building on McDonald's 1999 omega framework)	Karl Gustav Jöreskog
Type	Reliability coefficient	Hypothesis-testing latent variable model
Source fondatrice	Zumbo, B. D., Gadermann, A. M., & Zeisser, C. (2007). Ordinal versions of coefficients alpha and theta as measures of internal consistency for Likert rating scales. Journal of Modern Applied Statistical Methods, 6(1), 21–29.	Jöreskog, K. G. (1969). A general approach to confirmatory maximum likelihood factor analysis. Psychometrika, 34(2), 183–202.
Alias	omega ordinal, ordinal omega, polychoric omega, omega for ordinal data	CFA, confirmatory FA, measurement model, restricted factor analysis
Apparentées	3	4
Résumé	Ordinal McDonald's omega is a reliability coefficient designed for Likert-type and other ordinal rating scales. Unlike Cronbach's alpha, it bases its calculation on polychoric correlations among items — capturing the true latent relationships between ordinal responses — and uses factor-analytic loadings to estimate how much of the composite score variance is attributable to a common factor.	Confirmatory factor analysis tests a researcher-specified factor structure against observed data. Unlike exploratory approaches, the researcher decides in advance which indicators load on which latent factor, and the model is evaluated by how closely the implied covariance matrix reproduces the sample covariance matrix. CFA is central to scale validation, construct validity assessment, and measurement invariance testing.