Structural Equation Modeling
Fall 2011 – Dr. Adam Davey
Temple University – Department of Public Health
Selected quotes and my random thoughts as I take the SEM journey.
Here’s the text:
“Unlike multiple regression, though, SEM allows the analysis of curvilinear or interactive relations of both observed and latent variables.”
Whoa! Bring it.
“SEM readily allows the representation and estimation of possible
spurious associations because of common causes.”
On missing data (which is crucial to a proper SEM analysis)
“Also note that there is no magical statistical “fix” that
will remedy systematic data loss. About the best that can be done is to
attempt to understand the nature of the underlying data loss mechanism
and take preventive measures.”