Factorial Validity and Invariance of the 7-Item Generalized Anxiety Disorder Scale (GAD-7) Among Populations With and Without Self-Reported Psychiatric Diagnostic Status

Abstract

The 7-item Generalized Anxiety Disorder Scale (GAD-7) is commonly used to monitor anxiety symptoms. However, its factor structure has been inconsistent among competing models: unidimensional, two-dimensional, or higher order models. Additionally, it is unknown whether the scale has measurement invariance between populations with and without self-reported psychiatric diagnostic status. Participants were Japanese adults with self-reported anxiety disorder (AD; n = 479), self-reported AD and major depressive disorder (MDD; n = 314), or without self-reported psychiatric diagnostic status (self-reported non-MDD/AD; n = 654), who completed this questionnaire on the Internet. Confirmatory factor analyses showed the higher order model had similar fit indices to the unidimensional and two-dimensional factor models. For the higher order model of GAD-7, metric invariance was supported between the self-reported non-MDD/AD and self-reported AD status groups, and scalar invariance was supported between the self-reported AD status and self-reported AD with MDD status groups. Moreover, convergent and discriminant validity were consistent with previous findings in Western cultures. These results suggest that factor loadings are equivalent and the construct has the same meaning between the self-reported non-MDD/AD and self-reported AD status groups, and the total or sub-scale scores were comparable between self-reported AD status and self-reported AD with MDD status groups. The major limitation of this study is that the participants' diagnoses were self-reported, not confirmed by clinical structured interview. Further studies that incorporate clinical structured interviews are needed.

Keywords: Japanese; anxiety; factor structure; factorial validity; measurement invariance.