Structural Equation Modeling (SEM) for Satisfaction and Dissatisfaction Ratings; Multiple Group Invariance Analysis Across Scales with Different Response Format

The current study evaluates three hypothesized models on subjective well-being, comprising life domain ratings (LDR), overall satisfaction with life (OSWL), and overall dissatisfaction with life (ODWL), using structural equation modeling (SEM). A sample of 1,310 volunteering students, randomly assigned to six conditions, rated their overall life (dis)satisfaction and their (dis)satisfaction with six different life domains. Each condition used one of six response formats, differing in (1) orientation (horizontal vs. vertical), and (2) anchoring (0 to 10, -5 to +5, and Not numbered). The results of a confirmatory factor analysis (CFA) support a six-factor model of LDR based on satisfaction or dissatisfaction items. However, our findings indicate that the kind of response format used to obtain satisfaction and dissatisfaction ratings can affect the factor loadings. Our results indicate that the proposed models of OSWL, and ODWL fit the data well, and are able to predict OSWL and ODWL, respectively. Moreover, among six life domains, which figure as the latent variables in our models, psychological well-being was found to be the strongest predictor of both OSWL and ODWL.