Detecting Unobserved Heterogeneity in the Relationship between Subjective Well-Being and Satisfaction in Various Domains of Life Using the REBUS-PLS Path Modelling Approach: A Case Study

Social Indicators Research, 110 (1), pp. 281-304

31 Pages Posted: 22 Sep 2011 Last revised: 28 Dec 2013

Date Written: December 10, 2013

Abstract

We propose a model to estimate the direct and indirect effects of the relationship between subjective well-being and satisfaction in various domains of life using a partial least squares path modelling approach in a structural equation model framework. A drawback of these models is that they assume homogeneous behaviour over the observed set of units. To address this issue, Trinchera (Ph.D. thesis, University of Naples, 2007) and Esposito Vinzi et al. (Appl Stoch Models Bus Ind 28:439-458, 2008) proposed an algorithm, called the response-based unit segmentation in partial least squares (REBUS-PLS) path modelling, to detect sources of heterogeneity in both measurement and structural models. The REBUS-PLS allows researchers to identify classes of units with similar behaviours (with respect to the postulated model) and to estimate one model for each identified class (so-called ‘local models’). Applying the REBUS-PLS algorithm to our case study, we detected three main classes of units with similar behaviours and estimated three local models. We found, for example, that in the estimated model for the entire sample, the relationship between satisfaction with family and social life and subjective well-being is statistically significant. However, this result was not confirmed in all of the estimated local models.

Keywords: PLS path modelling, REBUS-PLS, Satisfaction in various domains of life, Subjective well-being, Unobserved heterogeneity

JEL Classification: C20, C30, C80, D01

Suggested Citation

Zanin, Luca, Detecting Unobserved Heterogeneity in the Relationship between Subjective Well-Being and Satisfaction in Various Domains of Life Using the REBUS-PLS Path Modelling Approach: A Case Study (December 10, 2013). Social Indicators Research, 110 (1), pp. 281-304, Available at SSRN: https://ssrn.com/abstract=1931250

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
30
Abstract Views
554
PlumX Metrics