Different specifications for LCA usin... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Anonymous posted on Monday, June 25, 2012 - 2:01 pm
I am trying to find examples of how to specify in Mplus the following 3 step approaches to using covariates in LCA: most likely class regression, probability regression and probability-weighted regression. For example, supposing I have 4 latent classes and wish to explore the relationship between class and age.

I have found the following example based on an initial 4 class run:

Variable: names are age cprob1 cprob2 cprob3 cprob4 class;
usevariables are
age cprob1 cprob2 cprob3 cprob4;
CLASSES = C (4);
TRAINING= cprob1-cprob4 (PROBABILITIES);
ANALYSIS: TYPE = MIXTURE;
STARTS 100 10;
MODEL: %OVERALL%
c#1 ON age;
c#2 ON age;
c#3 ON age;

Which type would this be an example of?

Many thanks in advance on your helpful comments.
 Linda K. Muthen posted on Monday, June 25, 2012 - 4:39 pm
This is probability regression. See the following paper which is available on the website for further information:

Clark, S. & Muthén, B. (2009). Relating latent class analysis results to variables not included in the analysis.
 Anonymous posted on Tuesday, June 26, 2012 - 10:08 am
Many thanks.
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: