Factor structure and internal consistency of the STAXI-2 anger expression items in a general population sample from Monterrey city, Mexico
There exits controversy about the factor structure of the anger expression items from the Revised State- Trait Anger Expression Inventory (STAXI-2). Three new items have been proposed to replace items 3, 10 and 17 with problems of internal consistency. The aims of this study were to contrast the fit...
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Online |
| Langue: | spa |
| Publié: |
Consorcio de Universidades Mexicanas A.C.
2015
|
| Accès en ligne: | https://psicumex.unison.mx/index.php/psicumex/article/view/279 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| Résumé: | There exits controversy about the factor structure of the anger expression items from the Revised State- Trait Anger Expression Inventory (STAXI-2). Three new items have been proposed to replace items 3, 10 and 17 with problems of internal consistency. The aims of this study were to contrast the fit and invariance of the four-factor model for the 24 anger expression items from the STAXI-2 across sex; in case of problems of internal consistency and factor definition, explore and contrast alternative factor models. The STAXI-2 anger expression scale with the inclusion of three new items was administrated to a non-probability sample of 120 women and 120 men from the general population. Items 3 and 17 showed internal consistency problems. The correlation between internalizing and externalizing factors was very high in the confirmatory factor analysis. Horn’s parallel analysis and Velicer’s criterion indicated that the number of factors is three. The expected two factors of control, and a non-expected factor with the internalizing and externalizing items (anger expression) were configured. The internal consistency of these three factors varied from acceptable to high. The fit to the data of 3-factor model and its properties of invariance across sex were acceptable by the chi-square/gl, RMSEA, CFI and SRMR indexes. It is concluded that the scale should be reduced to 22 items, does not bring advantages the introduction of the new items, and its structure is three factors. |
|---|
