Contributions to Bayesian Structural Equation Modeling

Structural equation models (SEMs) are multivariate latent variablemodels used to model causality structures in data. A Bayesian estimation and validationof SEMs is proposed and identi ability of parameters is studied. The latterstudy shows that latent variables should be standardized in the nalysis to ensure identi fiability. This heuristics is in fact introduced to deal with complex identi abilityconstraints. To illustrate the point, identi ability constraints are calculated in a marketing application, in which posterior draws of the constraints are derivedfrom the posterior conditional distributions of parameters