Accounting for unobserved heterogeneity has become a key concern to ensure the validity of results when applying partial least squares structural equation modeling (PLS-SEM). Recent methodological research in the field has brought forward a variety of latent class techniques that allow for identifying and treating unobserved heterogeneity. This chapter raises and discusses key aspects that are fundamental to a full and adequate understanding of how to apply these techniques in PLS-SEM. More precisely, in this chapter, we introduce a systematic procedure for identifying and treating unobserved heterogeneity in PLS path models using a combination of latent class techniques. The procedure builds on the FIMIXPLS method to decide if unobserved heterogeneity has a critical impact on the results. Based on these outcomes, researchers should use more recently developed latent class methods, which have been shown to perform superior in recovering the segment-specific model estimates. After introducing these techniques, the chapter continues by discussing themeans to identify explanatory variables that characterize the latent segments. Our discussion also broaches the issue of measurement invariance testing, which is a fundamental requirement for a subsequent comparison of parameters across groups by means of a multigroup analysis.
