Consequences of Not Conducting Measurement Invariance Tests in Cross-Cultural Studies: A Review of Current Research Practices and Recommendations

• Published in: Advances in developing human resources Vol. 21; no. 4; pp. 466 - 483
• Main Authors: Jeong, Shinhee, Lee, Yunsoo
• Format: Journal Article
• Language: English
• Published: Los Angeles, CA SAGE Publications 01-11-2019; SAGE PUBLICATIONS, INC
• Subjects: Cross cultural studies; Discriminant analysis; Employee development; Research methodology; Researchers; cross-cultural study; comparative study; measurement invariance; multigroup confirmatory factor analysis
• DOI: 10.1177/1523422319870726
• EISSN: 1552-3055
• ISSN: 1523-4223

The Problem
Cross-cultural research has received substantial attention from both academia and practice as it contributes to expand current theory and implements culturally successful human resource strategies. Although the quantity of this type of research has increased, several researchers have raised methodological concerns that the majority of cross-cultural research has simply assumed or ignored measurement invariance.
The Solution
In this article, we first provide the meaning for measurement invariance, discuss why it is important, and then explain stepwise confirmatory factor analysis procedures to test measurement invariance. We also diagnose the current research practice in the field of human resource development (HRD) based on a review of cross-cultural, comparative research published in the major HRD journals. Finally, we demonstrate that the group difference test results that have been found without ensuring measurement invariance can, in fact, be false.
The Stakeholders
This article contributes to the HRD literature and practice in two ways. First, HRD researchers are invited to recognize the importance of sophisticated research methodology, such as measurement invariance, and to examine item bias across different groups so they can make a meaningful and valid comparison. The same attention is advisable to any practitioner who attempts to identify group differences using multinational/cultural data. This article also provides HRD scholars and practitioners with specific multigroup confirmatory factor analysis (MGCFA) procedures to facilitate empirical tests of measurement models across different groups and thus disseminate the methodological advances in the field of HRD. It is our hope that the present article raises awareness, circulates relevant knowledge, and encourages more HRD scholars to think critically about measurement.