Abstract
OBJECTIVE
Measurement invariance deals with whether the expected scores on a measure are the same or different across different groups when the groups have the same level of the underlying latent trait scores. The study used multiple-group confirmatory factor analysis (CFA) to examine measurement invariance across male and female adolescent self-ratings of the ADHD symptoms (recoded as binary scores).
METHOD
To accomplish this, 178 male and 185 female adolescents, between 12 and 17 years of age, completed an ADHD rating scale.
RESULTS
For the measurement model, the results support the invariance for the configural model (same factor structure and the same items associated with the latent factors), metric invariance (same strength of the associations of items with the factors) for the factor loadings of 17 of the 18 symptoms, and all the error variances. For the construct model, there was invariance for the inattention (IA) and hyperactivity/impulsivity (HI) latent factor variances, covariances, and mean scores. Thus, there was good support for gender equivalency for the ADHD symptoms.
CONCLUSION
These findings extend existing gender invariance data for the ADHD symptoms. The theoretical and clinical implications of the findings as well as the revision implications for Diagnostic and Statistical Manual of Mental Disorders (5th ed.; DSM-V) are discussed.
Collapse