Contributions to Bayesian Structural Equation Modeling

Abstract

Structural equation models (SEMs) are multivariate latent variable models used to model causality structures in data. A Bayesian estimation and validation of SEMs is proposed and identifiability of parameters is studied. The latter study shows that latent variables should be standardized in the analysis to ensure identifiability. This heuristics is in fact introduced to deal with complex identifiability constraints. To illustrate the point, identifiability constraints are calculated in a marketing application, in which posterior draws of the constraints are derived from the posterior conditional distributions of parameters.

The Comparison of Classical and Bayesian Structural Equation Models Through Ordered Categorical Data: A Case Study of Banking Service Quality

“…These studies not only prepare theoretical results but also try to produce important practical values. The BSEM technique, called Bayesian approach and based on the Bayesian approach, has been applied to substantive real research in various disciplines, including a much wider class of models, such as marketing research, diabetes research, medicine, psychology, coastal management and water quality, job satisfaction and life satisfaction [3,[6][7][8][9][10][11][12].…”