ABSTRACT
Structural equation modelling (SEM) is a fundamental analytical tool for any behavioral researcher (Bagozzi and Yi 2012; Iacobucci 2009). SEM represents a natural extension of factor analysis and regression analysis and is therefore used to investigate relationships between observed variables (i.e. quantities that can be measured directly) and latent variables (i.e. concepts that cannot be measured directly), as well as causal relationships between latent variables. Thanks to its flexibility, SEM may be applied to a wide range of research problems, from construct measurement and the assessment of psychometric properties to theory testing and path analysis (Byrne 1998).
