Answers are grounded in this paper and cite their sources.
Investigating measurement invariance is an essential prerequisite for meaningful evaluations of psychological questionnaires. Because the widely-used approach of treating MI as a binary decision does not enable inferences about the practical implications of non-invariance, effect sizes for MI – most notably dMACS – were proposed. So far, such effect sizes have only been defined for models with simple structure, which consequently limits their applicability. In this paper, we extend dMACS and subsequent effect sizes of measurement nonequivalence to general factor analytic models, rendering them universally applicable. We provide corresponding implementations with optimal computational complexity.
No takes yet. Share an insight, caveat, or question.
Schuhbeck et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: