Abstract
This study was conducted to test for method bias stemming from mixing positively and negatively worded items in a widely used measure of family functioning, the Systemic Clinical Outcomes in Routine Evaluation (SCORE). Data were collected from a community sample of 377 U.S. adults with children in the household, with 32% reporting greater family difficulties than a clinical pre-therapy average and 66% reporting greater difficulties than a clinical post-therapy average. Confirmatory factor analyses (CFA) were performed to test two models: Model 1, a unidimensional model in which items represented a single theoretical construct and Model 2, a multidimensional model in which items represented a method dimension (i.e., positively worded or negatively worded) as well as an underlying theoretical construct. Fit indices showed that Model 2 fit the data better than Model 1 for all dimensions tested, suggesting that method bias had detrimental effects on the factor structure of dimensions of the SCORE.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have