Still comparing apples with oranges? Some thoughts on the principles and practices of measurement invariance testing.

This editorial seeks to encourage European Journal of Psychological Assessment authors to take a critical approach to the use of multi-group confirmatory factor analysis (CFA) for invariance testing. The authors highlight three aspects surrounding the principles and practices of invariance testing via multi-group CFA: First, the application of model fit criteria to compare nested invariance models should always be evaluated considering the complexity of measurement models, the study sample, and the treatment of data. Second, standard invariance testing procedures, including multi-group CFA, have certain limitations. Third, the authors believe that the analysis of differential item functioning provides more specific information about whether certain items in a scale or test are invariant across groups or over time. This procedure can supplement more global tests of measurement invariance and thus strengthen the creation of a validity argument. (PsycINFO Database Record (c) 2018 APA, all rights reserved)
Source: European Journal of Psychological Assessment - Category: Psychiatry & Psychology Source Type: research