Construct Validity of Attributional Style: Modeling Context-Dependent Item Sets in the Attributional Style Questionnaire

• Published in: Educational and psychological measurement Vol. 59; no. 5; pp. 804 - 820
• Main Authors: Higgins, N. C., Zumbo, Bruno D., Hay, Jana L.
• Format: Journal Article
• Language: English
• Published: Thousand Oaks, CA SAGE Publications 01.10.1999; Sage; Educational and Psychological Measurement, etc
• Subjects: Adults; Attribution Style Questionnaire; Attribution Theory; Biological and medical sciences; Confirmatory Factor Analysis; Construct Validity; Context Effect; Fundamental and applied biological sciences. Psychology; Personality. Affectivity; Psychology. Psychoanalysis. Psychiatry; Psychology. Psychophysiology; Psychometrics; Questionnaires; Test Items; Context; Human; Test validation; Construct validity; Data analysis; Questionnaire; Confirmatory factor analysis; Attributional Style Questionnaire Peterson et al; Psychometrics; Personality; Cognitive style; Attribution
• ISSN: 0013-1644; 1552-3888
• DOI: 10.1177/00131649921970152

The format of the Attributional Style Questionnaire (ASQ) lends itself to a consideration of context-dependent item sets (CDIS) and a reevaluation of the factor structure of the questionnaire. Confirmatory factor analysis of data from 1,346 ASQ respondents revealed that adequate fit was provided by a three-factor (locus, stability, globality) attributional style model that included CDIS. The findings demonstrated that CDIS introduced extra covariation in people’s responses to the ASQ events—covariation that has been accounted for in the past as person (latent) variables or not accounted for at all. The authors argue for the inclusion of CDIS in psychometric models of the ASQ and in models of other attributional style measures that have the same format as the ASQ. In addition, when measuring attributional style, one must account for the person in the situations that are relevant to the style—CDIS allow one to do so.