Reliability of the Factor Index of the Wais-III Adapted for the Brazilian Population
A new approach is presented for the assessment of the score reliability of psychological instruments by means of orthogonalization of the latent variables and the estimation of the corresponding coefficients of composite reliability. The present study used this approach to investigate the reliabilit...
| Autores: | , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2015 |
| País: | Brasil |
| Institución: | Universidade Presbiteriana Mackenzie (UPM) |
| Repositorio: | Psicologia (Universidade Presbiteriana Mackenzie. Online) |
| Idioma: | portugués |
| OAI Identifier: | oai:ojs.editorarevistas.mackenzie.br:article/7511 |
| Acceso en línea: | http://editorarevistas.mackenzie.br/index.php/ptp/article/view/7511 |
| Access Level: | acceso abierto |
| Palabra clave: | modelo de los factores precisión fiabilidade compuesta habilidades cognitivas teste de inteligência modelo bifactor precisão confiabilidade composta bifactor modes accuracy composite reliability cognitive ability intelligence test |
| Sumario: | A new approach is presented for the assessment of the score reliability of psychological instruments by means of orthogonalization of the latent variables and the estimation of the corresponding coefficients of composite reliability. The present study used this approach to investigate the reliability of the Wais-III index scores, adapted for the Brazilian population. Various models were tested: the one with the best fit was the bifactor model with one general factor and four specific factors, corresponding to the Wais-III index scores. For the general factor, high reliability coefficients were found (composite reliability [CR] = .96; hierarchical omega [?] = .94); yet the specific dimensions, after controlling the effect of the general dimension, showed low reliability coefficients (CR ? .35; ? ? .14). On basis of these findings, extreme caution is recommended concerning the interpretation of the Wais-III index scores, since most of the variance of those scores seems to be related to the general dimension. |
|---|