Comparer des méthodes

	Alpha de Cronbach bayésien	Analyse factorielle confirmatoire bayésienne (AFCB)	Théorie de la généralisabilité (Théorie G)
Domaine	Psychométrie	Psychométrie	Psychométrie
Famille	Latent structure	Latent structure	Latent structure
Année d'origine	2011 (Bayesian form); 1951 (classical alpha)	2007–2012	1963–1972
Auteur d'origine	Padilla & Zhang (Bayesian adaptation); Cronbach (classical alpha, 1951)	Sik-Yum Lee; Bengt Muthén and Tihomir Asparouhov	Lee J. Cronbach, Goldine Gleser, Harinder Nanda, Nageswari Rajaratnam
Type	Bayesian reliability estimation	Bayesian latent variable model	Variance-components reliability model
Source fondatrice	Padilla, M. A., & Zhang, G. (2011). Estimating internal consistency using Bayesian methods. Journal of Modern Applied Statistical Methods, 10(1), 277–286.	Lee, S.-Y. (2007). Structural Equation Modeling: A Bayesian Approach. Wiley. ISBN: 978-0470024232	Cronbach, L. J., Gleser, G. C., Nanda, H. & Rajaratnam, N. (1972). The Dependability of Behavioral Measurements: Theory of Generalizability for Scores and Profiles. Wiley.
Alias	Bayesian alpha, Bayesian internal consistency, Bayes-alpha, posterior alpha	BCFA, Bayesian CFA, Bayesian structural equation measurement model, Bayes-CFA	G-theory, G-study / D-study framework, variance components reliability
Apparentées	2	4	4
Résumé	Bayesian Cronbach's alpha applies Bayesian inference to estimate the classical internal-consistency coefficient, yielding a full posterior distribution over alpha rather than a single point estimate. This allows researchers to quantify uncertainty with credible intervals and incorporate prior knowledge, making reliability assessment more informative — especially with small or skewed samples.	Bayesian confirmatory factor analysis tests a pre-specified factor structure using Bayesian inference. Instead of point estimates with p-values, it produces full posterior distributions for loadings, factor correlations, and residual variances, allowing the researcher to incorporate prior knowledge and propagate parameter uncertainty naturally.	Generalizability Theory is a psychometric framework that decomposes observed score variance into multiple sources — persons, items, raters, occasions, and their interactions — using analysis of variance. It replaces the single reliability coefficient of classical test theory with a family of coefficients that tell researchers how well scores generalize across different measurement conditions.