Factor scores as endogenous variables PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Michael T Weaver posted on Monday, September 09, 2013 - 12:15 pm
I read posts RE: using factor scores as endogenous variables, along with the Plausible Values for Latent Variables Technical Report and the Multiple Imputation with MPLUS article.

I would like to use a Bayes approach to test a model composed of those (Bayes-estimated) factor scores.

Would you please point me to one or more examples of how to do this in MPLUS (I'm using Version 7.11)?

Probably my being dense, but I could not find anything in my search of the web site nor the manual, nor could I figure out how (that is, syntax) to incorporate the information in the SAVEDATA: file for the final Bayes model testing...

Thanks in advance...

Michael
 Linda K. Muthen posted on Tuesday, September 10, 2013 - 10:50 am
See Example 11.7 for generating and saving the plausible values. See Example 13.13 for using them in an analysis.
 Katherine Paschall posted on Thursday, August 18, 2016 - 8:05 am
Hello, I plan to use the aforementioned technique for estimating factor scores; I plan to use the plausible values in a model with both latent and observed variables. I am choosing this method to reduce the computational burden - the model has 3 latent factors already, and I am looking to add 6 more (3 socio-emotional constructs at 2 time points). I have not seen a model that includes both factor scores and latent variables - is this reasonable?

And, after estimation, can factor scores be modeled as dependent variables?
 Bengt O. Muthen posted on Thursday, August 18, 2016 - 10:37 am
Yes on both.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: