A confirmatory bifactor analysis of the hospital anxiety and depression scale in an Italian community sample

Background: The Hospital Anxiety and Depression Scale (HADS) is a widely used self-report measure to assess emotional distress in clinical populations. As highlighted in recent review studies, the latent structure of the HADS is still an issue. The aim of this study was to analyze the factorial structure of the HADS in a large community sample in Italy, and to test the invariance of the best fitting model across age and gender groups. Methods: Data analyses were carried out on a sample of 1.599 participants proportionally stratified according to the Italian census population pyramid. Participants aged 18 to 85 years (females = 51.8%), living in eight different regions of Italy, voluntarily participated in the study. The survey questionnaire contained the HADS, Health Status questions, and sociodemographic variables. Results: Confirmatory factor analysis indicated that a bifactor model, with a general psychological distress factor and two orthogonal group factors with anxiety and depression, was the best fitting one compared to six alternative factor structures reported in the literature, with overall good fit indices [Non-normed Fit Index (NNFI) = .97; Comparative Fit Index (CFI) = .98; Root Mean-Square Error of Approximation (RMSEA) = .04]. Multi-group analyses supported total invariance of the HADS measurement model for males and females, and for younger (i.e., 18-44 years old) and older (i.e., 45-85 years old) participants. Our descriptive analyses showed that females reported significant higher anxiety and general distress mean scores than males. Moreover, older participants reported significant higher HADS, anxiety and depression scores than younger participants. Conclusions: The results of the present study confirmed that the HADS has good psychometric properties in an Italian community sample, and that the HADS scores, especially the general psychological distress one, can be reliably used for assessing age and gender differences. In keeping with the most recent factorial studies, our analysis supported the superior fit of a bifactor model. However, the high factor loadings on the general factor also recommend caution in the use of the two subscales as independent measures.