The Advancement of Measurement Invariance Testing in Cross-Cultural Research in the Period 1999–2020. Executing Rather Than Scrutinizing?

Abstract

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal Take down policyIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Why we need to rethink measurement invariance: The role of measurement invariance for psychological science

“…A practical concern is that multigroup CFA applied to datasets with more than a few samples is inevitably leading to the rejection of measurement invariance (Gardiner & Funder, 2023; for a more positive assessment, see Van Herk & Goldman, 2022). Establishing scalar invariance in this context is particularly challenging.…”

“…However, most instruments have a limited number of items which are a) unlikely to represent a random selection out of a universe of indicators and b) not conditionally independent of each other given the latent variable (Robitzsch & Lüdtke, 2023). Considering the limited content covered by a small number of items within most measures, removing one or more items will likely changes the meaning of the construct being measured (Singh, 1995;Steenkamp & Baumgartner, 1998;Van Herk & Goldman, 2022) and the interpretation of any pairwise difference becomes open to alternative interpretations. Robitzsch and Lüdtke (2023) argue that the interpretation of a misspecified (that is poorly fitting) multigroup factor model is conceptually cleaner than a well-fitting model in each sample that relies on different parameters in each sample.…”

“…It is often claimed that this perspective has become the mainstream of psychological research (Gardiner & Funder, 2023). This normative claim is strongly contradicted by the observation that that the majority of currently published articles ignore measurement invariance (Boer et al, 2018;Maassen et al, 2023;Van Herk & Goldman, 2022). Furthermore, a number of researchers have recently argued that measurement invariance is counterproductive and irrelevant for empirical research (Gardiner & Funder, 2023;Robitzsch & Lüdtke, 2023;Welzel et al, 2021).…”