APROXIMACIÓN CONCEPTUAL Y PRÁCTICA A LOS MODELOS DE ECUACIONES ESTRUCTURALES

This methodological article explains a conceptual and practical approach to Structural Equation Models or Structural Equation Modeling (SEM). SEMs are considered among the most powerful tools for the study of causal relationships in non-experimental data. They are a combination of factor analysis and multiple regression and are composed of two components: the measurement model and the structural model. The measurement model describes the relationship between a series of observable variables; while in the structural model the relationships between variables are hypothesized; i.e., the relationships between latent variables are described with the use of arrows. Performing a SEM involves five stages: (1) A specification of the Model; (2) Identification of the Model; (3) Estimation of the Model; (4) Evaluation of the Model and (5) Re-specification of the Model. This article provides a series of guidelines on “best practices” for SEM analysis, with examples using the AMOS program.