Dear RG members.
In epidemiological research, control of confounding is a core concept.
Structural Equations Models (SEM) appear now as an alternative for epidemiological analyses.
But, I could not find appropriate guidelines about how control for confounding variables in SEM analyses in the current literature.
An important issue: controlling for confounding should depend on the number of endogenous and exogenous variables in the SEM model?
Thank you.
There is a discussion thread on the MPlus website that may be helpful. http://www.statmodel.com/discussion/messages/11/2656.html?1408065214
Even its in the context of longitudinal evaluations, the book of Little is proably helpful, since different types of controlling for confounders are discussed and examples are offered.
Best
Little, P. T. D. (2013). Longitudinal structural equation modeling. Guilford Press.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling