Guidelines for Treating Unobserved Heterogeneity in Tourism Research: A Comment on Marques and Reis (2015)

Abstract

Accounting for heterogeneity in tourism studies remains important to avoid parameter bias (e.g., Mazanec, 2000; Mazanec, Ring, Stangl, & Teichmann, 2010) when employing analysis techniques such as regression (e.g., Ye, Zhang, & Yuen, 2013), partial least squares structural equation modeling (PLS-SEM) (e.g., Song, van der Veen, Li, & Chen, 2012), or covariance structural equation modeling (CB-SEM) (e.g., Jurowski & Gursoy, 2004). Heterogeneity can come in two forms. First, heterogeneity can be observable in that differences between two or more groups of data relate to observable characteristics (e.g., Dolnicar, 2004). Researchers can use these observable characteristics to partition the data into separate groups of observations and compare the group-specific estimates by means of multigroup comparisons. Second, heterogeneity can be unobserved in that it does not depend on one specific observable characteristic or combinations of several characteristics (e.g., Mazanec, 2000, 2001). To identify and treat unobserved heterogeneity, researchers can draw on a variety of latent class techniques. For instance, Assaf, Oh, and Tsionas (2015) employ Bayesian finite mixture modeling within CB-SEM, and Marques and Reis (2015) finite mixture modeling within PLS-SEM. It is the latter approach that this commentary focuses on.