Factor Mixture Modeling with Covariat... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Eunsoo Cho posted on Thursday, December 06, 2018 - 2:49 pm
Dear Drs. Muthen,

I fit a factor mixture model that enumerated 3 profiles based on the 3-factor model. I then want to investigate the effect of the latent profile variable on the distal outcome, controlling for covariates. To do this, I tried applying the manual BCH estimation approach described in Asparouhov & Muthen (2018, pp. 10-12; Mplus webnote 21. However, I got several warnings and errors in the second step. For instance,

*** ERROR
The following MODEL statements are ignored:
* Statements in the OVERALL class:
LC ON C#1
LC ON C#2
LRECAL ON C#1
LRECAL ON C#2
RC ON C#1
RC ON C#2
RRECAL ON C#1
RRECAL ON C#2
FLUE ON C#1
FLUE ON C#2
*** ERROR
One or more MODEL statements were ignored. These statements may be
incorrect or are only supported by ALGORITHM=INTEGRATION.


I am wondering if that approach does not work in the FMM framework. If the BCH approach works in FMM, could you please help solve the problems?
 Bengt O. Muthen posted on Thursday, December 06, 2018 - 3:23 pm
The influence of a latent class variable C on a distal outcome Y is not obtained by Y ON C, but instead by the different Y means for the different C classes.
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: