Abstracts
Résumé
Au cours des dernières décennies, certains auteurs ont suggéré de rejeter le coefficient alpha (α) de Cronbach (1951) pour adopter le coefficient oméga (ω) de McDonald (1985, 1999) basé sur un modèle d’analyse factorielle. Après avoir présenté certaines limites inhérentes à l’α, nous présentons le coefficient ω et ses déclinaisons en poursuivant deux objectifs : comprendre la logique théorique derrière les coefficients de fidélité oméga et exposer les spécificités des coefficients ω sur le plan de leur méthode de calcul. À cet effet, nous distinguons les conditions d’usage des différentes formes d’ω (total ou hiérarchique, dans le cadre d’une AFE ou d’une AFC). Un exemple d’analyse et des recommandations sont proposés pour mieux argumenter la fidélité des scores.
Mots-clés :
- oméga,
- fidélité des scores,
- modèle d’analyse factorielle,
- adéquation des données
Abstract
In recent decades, some authors have proposed rejecting Cronbach’s alpha (α) coefficient (1951) to adopt McDonald’s omega (ω) coefficient (1985, 1999) which is based on a factor analysis model. After presenting some inherent limits of the α, this article follows two aims : (i) understanding the theoretical logic behind omega coefficients and (ii) presenting ω coefficients’ specificities regarding their computation method. To this end, we identify conditions for the use of the different forms of ω (total or hierarchical, with an EFA or CFA). An example of analysis and recommendations are suggested to better argue the score reliability.
Keywords:
- omega,
- reliability of scores,
- factor analysis model,
- model fit
Resumo
Nas últimas décadas, alguns autores sugeriram a rejeição do coeficiente alfa (α) de Cronbach (1951) para se adotar o coeficiente ómega (ω) de McDonald (1985, 1999) baseados num modelo de análise fatorial. Após a apresentação de certas limitações inerentes ao α, apresentamos o coeficiente ω e as suas variações, prosseguindo dois objetivos : compreender a lógica teórica subjacente aos coeficientes de fidelidade ómega e expor as especificidades dos coeficientes ω em termos do seu método de cálculo. Para este fim, distinguimos as condições de uso das diferentes formas de ω (total ou hierárquico, no quadro de um AFE ou AFC). Um exemplo das análises e das recomendações são propostas para melhor argumentar a fidelidade das pontuações.
Palavras chaves:
- ómega,
- fidelidade das pontuações,
- modelo de análise fatorial,
- adequação dos dados
Appendices
Références
- Bonett, D. (2021). Statistics for psychologists : An introduction to multivariate statistical models (vol. 4) [document en préparation].
- Bourque, J., Doucet, D., LeBlanc, J., Dupuis, J. et Nadeau, J. (2019). L’alpha de Cronbach est l’un des pires estimateurs de la consistance interne : une étude de simulation. Revue des sciences de l’éducation, 45(2), 78-99. https://doi.org/g4pm
- Brunner, M., Nagy, G. et Wilhelm, O. (2012). A tutorial on hierarchically structured constructs. Journal of Personality, 80(4), 796-846. https://doi.org/fccf97
- Cho, E. (2016). Making reliability reliable : A systematic approach to reliability coefficients. Organizational Research Methods, 19(4), 651-682. https://doi.org/f838w6
- Cho, E. (2021). Neither Cronbach’s alpha nor McDonald’s omega : A commentary on Sijtsma and Pfadt. Psychometrika. https://doi.org/g4pn
- Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika, 16(3), 297-334. https://doi.org/cc5
- Deng, L. et Chan, W. (2017). Testing the difference between reliability coefficients alpha and omega. Educational and Psychological Measurement, 77(2), 185-203. https://doi.org/gfj8nh
- Dunn, T. J., Baguley, T. et Brunsden, V. (2013). From alpha to omega : A practical solution to the pervasive problem of internal consistency estimation. British Journal of Psychology, 105(3), 399-412. https://doi.org/f2dpm2
- Edwards, M. C. (2013). Purple unicorns, true models, and other things I’ve never seen. Measurement : Interdisciplinary Research and Perspectives, 11(3), 107-111. https://doi.org/g4pp
- Flora, D. B. (2020). Your coefficient alpha is probably wrong, but which coefficient omega is right? A tutorial on using R to obtain better reliability estimates. Advances in Methods and Practices in Psychological Science, 3(4), 484-501. https://doi.org/ghj99z
- Greene, V. L. et Carmines, E. G. (1980). Assessing the reliability of linear composites. Sociological Methodology, 11, 160-175. https://doi.org/ckt88n
- Guttman, L. (1945). A basis for analyzing test-retest reliability. Psychometrika, 10(4), 255-282. https://doi.org/b45tjm
- Hayes, A. F. et Coutts, J. J. (2020). Use omega rather than Cronbach’s alpha for estimating reliability. But... Communication Methods and Measures, 14(1), 1-24. https://doi.org/ggwd6m
- Jackson, E. H. et Agunwamba, C. C. (1977). Lower bounds for the reliability of the total score on a test composed of nonhomogeneous items : Algebraic lower bounds. Psychometrika, 42(4), 567-578. https://doi.org/d98rr5
- Jensen, A. R. et Weng, L.-J. (1994). What is a good g? Intelligence, 18(3), 231-258. https://doi.org/ddb8b3
- Kelley, K. et Pornprasertmanit, P. (2016). Confidence intervals for population reliability coefficients : Evaluation of methods, recommendations, and software for homogeneous composite measures. Psychological Methods, 21(1), 69-92. https://doi.org/f8fq9j
- Kline, R. B. (2016). Principles and practice of structural equation modeling (4e éd.). Guilford Press.
- Kuder, G. F. et Richardson, M. W. (1937). The theory of the estimation of test reliability. Psychometrika, 2(3), 151-160. https://doi.org/czx5nr
- Lord, F. M., Novick, M. R. et Birnbaum, A. (1968). Statistical theories of mental test scores. Addison-Wesley.
- Maydeu-Olivares, A., Coffman, D. L. et Hartmann, W. M. (2007). Asymptotically distribution-free (ADF) interval estimation of coefficient alpha. Psychological Methods, 12(2), 157-176. https://doi.org/dv8gpk
- McDonald, R. P. (1985). Factor analysis and related methods. Lawrence Erlbaum.
- McDonald, R. P. (1999). Test theory : A unified treatment. Lawrence Erlbaum.
- McNeish, D. (2018). Thanks coefficient alpha, we’ll take it from here. Psychological Methods, 23(3), 412-433. https://doi.org/gcsk2k
- Newton, P. et Shaw, S. (2014). Validity in educational and psychological assessment. SAGE.
- Parkes, J. (2007), Reliability as argument. Educational Measurement : Issues and Practice, 26(4), 2-10. https://doi.org/ccwsdf
- Pfadt, J. M., van den Bergh, D., Sijtsma, K., Moshagen, M. et Wagenmakers, E. J. (2021). Bayesian estimation of single-test reliability coefficients. Multivariate Behavioral Research, 1-30. https://doi.org/g4pr
- Raîche, G. (2002). Le dépistage du sous-classement aux tests de classement en anglais, langue seconde, au collégial. Collège de l’Outaouais. https://eduq.info/xmlui/bitstream/handle/11515/1012/raiche_PAREA_2001_depistage.pdf
- Raykov, T. (1997). Scale reliability, Cronbach’s coefficient alpha, and violations of essential tau-equivalence with fixed congeneric components. Multivariate Behavioral Research, 32(4), 329-353. https://doi.org/d4mfcg
- Raykov, T. (2001). Bias of coefficient alpha for fixed congeneric measures with correlated errors. Applied Psychological Measurement, 25(1), 69-76. https://doi.org/fk938x
- Raykov, T., Dimitrov, D. M. et Asparouhov, T. (2010). Evaluation of scale reliability with binary measures using latent variable modeling. Structural Equation Modeling, 17(2), 265-279. https://doi.org/10.1080/10705511003659417
- Raykov, T. et Marcoulides, G. A. (2011). Introduction to psychometric theory. Routledge.
- Raykov, T. et Marcoulides, G. A. (2019). Thanks coefficient alpha, we still need you! Educational and Psychological Measurement, 79(1), 200-210. https://doi.org/gf4j8w
- Revelle, W. (2019) psych : Procedures for psychological, psychometric and personality research – R Package Version 1.9.12. Northwestern University, Evanston, IL. https://CRAN.R-project.org/package=psych
- Revelle, W. et Condon, D. M. (2019). Reliability from α to ω : A tutorial. Psychological Assessment, 31(12), 1395-1411. https://doi.org/gf527p
- Sijtsma, K. (2009). On the use, the misuse, and the very limited usefulness of Cronbach’s alpha. Psychometrika, 74(1), 107-120. https://doi.org/c76r6c
- Sijtsma, K. et Pfadt, J. M. (2021). Invited review part II : On the use, the misuse, and the very limited usefulness of Cronbach’s alpha : Discussing lower bounds and correlated errors. Psychometrika. https://doi.org/gmwnj5
- Stanley, L. M. et Edwards, M. C. (2016). Reliability and model fit. Educational and Psychological Measurement, 76(6), 976-985. https://doi.org/g4ps
- Trizano-Hermosilla, I. et Alvarado, J. M. (2016). Best alternatives to Cronbach’s alpha reliability in realistic conditions : Congeneric and asymmetrical measurements. Frontiers in Psychology, 7, 769. https ://doi.org/gfjz27
- Westfall, P. et Henning, K. (2013). Understanding advanced statistical methods. CRC Press.