Class variable as mediator PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Scott C. Roesch posted on Tuesday, October 31, 2017 - 6:53 am
I have a fairly complicated mediation model that I would like to test, and I am wondering if it is practicially possible to test all parameters simultaneously in MPlus. I have run a preliminary LCA and determined that the 3-class solution was the best-fitting. Herein lies my issue, this nominal variable will be the mediator in an SEM model. This variable will be predicted by multiple covariates and then predict my distal outcomes. Is it possible to test these relationships in the model given the mediator is general categorical? Related to this, can the 3-STEP APPROACH be used as well?
 Bengt O. Muthen posted on Tuesday, October 31, 2017 - 12:08 pm
You find writings on this at our Mediation web page:

See especially the book,

Muthén, B., Muthén, L. & Asparouhov, T. (2016). Regression And Mediation Analysis Using Mplus. Los Angeles: Muthén & Muthén.

and also

Muthén, B. (2011). Applications of causally defined direct and indirect effects in mediation analysis using SEM in Mplus. Click here to download the paper.

You find Mplus scripts at

see the Table 8.35 run.

3-step should be possible but I don't have any scripts available for that.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message