3
$\begingroup$

I've little background on SEM. Now I want to focus on its theoretical aspects like statistical model, model estimation and model evaluation. The seminal book on this topic is by Bollen: Structural Equations with Latent Variables. Unfortunately, this book is not in my access in my region. I wonder if there are any online class material or articles available freely to fulfil my requirements. Thanks in advance.

$\endgroup$

3 Answers 3

4
$\begingroup$

Perhaps this previous discussion might be useful to take a look at.

In addition to this, I know the OpenMx team has numerous examples of how to implement and estimate various kinds of SEMs using the OpenMx package in R.

$\endgroup$
1
3
$\begingroup$

There are two precursors to SEM: Factor Analysis, coming from psychology, and Path Analysis, coming from genetics. You might want to look at some of the materials on these two topics.

Path analysis started with relatively simple, highly structured relationships and some of these might be informative. A relatively accessible source is at Columbia: https://www.publichealth.columbia.edu/research/population-health-methods/path-analysis.

SEM assumes you have relatively strong theory and model structures that are somewhat rigid, based on your theory.

$\endgroup$
2
$\begingroup$

This video by Johny Lin at UCLA is great. Its basically a full structural equation model (SEM) course in a single video.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.