SEM Episode 4: The Structural Equation Model

In this episode of Office Hours, Patrick combines elements of path analysis and factor analysis to define the general structural equation model. ...

He begins by briefly reviewing path analysis and the assumption of perfect measurement reliability. He then briefly reviews the confirmatory factor analysis model and highlights that latent variables are allowed to covary with one another, but no directed (or structural) relations are estimated. Next, he brings these two concepts together to define the general SEM that allows for manifest variables, latent variables, and regression structures. He describes the six core steps in model building and concludes with some of the challenges faced when defining and evaluating more complex models.

Bollen, K. A. (1989). Structural Equations with Latent Variables John Wiley & Sons New York.

Hoyle, R. H. (Ed.). (2012). Handbook of structural equation modeling. Guilford Press.

Schumacker, R. E., & Lomax, R. G. (2004). A beginner's guide to structural equation modeling. Psychology Press.