Observed and Unobserved Heterogeneity
Learn about the two types of heterogeneity
In this short lecture, we briefly discuss an advanced topic in PLS-SEM: The role and treatment of observed and unobserved heterogeneity. Specifically, we introduce the concept of multigroup analysis, contrast it with the analysis of interaction effects, and highlight the role of measurement invariance assessment. We also briefly discuss latent class analysis as a means to identify and treat unobserved heterogeneity. The full lecture "PLS-SEM: A comprehensive introduction" discusses each of these topics in detail and gives concrete recommendations on how to implement corresponding analyses in PLS-SEM.
- 10-minute sample video discussing the role and treatment of observed and unobserved heterogeneity in PLS-SEM
- Offers guidance regarding the right choice of method when heterogeneity is a concern
- Highlights the role of measurement invariance assessment in PLS-SEM
Christian M. Ringle is a Professor of Management at the Hamburg University of Technology (TUHH), Germany, and an Adjunct Professor at the Waikato Management School, New Zealand. His research has been published in journals such as International Journal of Research in Marketing, Information Systems Research, Journal of the Academy of Marketing Science, MIS Quarterly, and Tourism Management. He co-developed the SmartPLS software and regularly teaches doctoral seminars on multivariate statistics, especially the PLS-SEM method.