Psychometric properties of the self-reporting questionnaire (SRQ-20): Measurement invariance across women from Brazilian community settings

Background: SRQ-20 is a validated screening tool for common psychiatric disorders in several countries. Exploration of the latent structure of this instrument resulted in conflicting evidence. This study aimed to explore the latent structure of SRQ-20 among Brazilian women from community settings. We also tested the model invariance across different sociodemographic conditions. Methods: Exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) were conducted on a sample of 1668 women from four different geographical regions of Brazil. Invariance of the model was tested through multi-group CFA according to sociodemographic variables. Results: EFA has shown two potential solutions with two and three factors. CFA resulted in indices of the two-factor solution slightly worse than the three-factor solution. Invariance testing has shown this model was not invariant across cities, but was invariant across different social classes. The structure was also invariant for the two lower educated groups. The respecifled model (i.e., excluding item 16) was not invariant across groups with different educational levels. Conclusion: The three-factor solution seems to be the most suitable model of SRQ-20 for Brazilian women in community settings. Furthermore, sociodemographic variables seem to reflect on the latent structure of this instrument. Validation of screening tools should consider sociodemographic variables. (C) 2014 Elsevier Inc. All rights reserved.