Questions with factor mixture model

[Celia Shi]

Does anyone ever use Stata to run factor mixture model? It seems that most people use Mplus to run factor mixture model. I have not used Mplus and would like to explore if Stata can do it. Many thanks!

[wbuchanan]

Stata has the capability to fit mixture models, but there are no native commands to do so. There are some user written commands that you could use. If you search for fmm you'll find one example in the SSC archives that does this.

[Celia Shi]

Stata has the capability to fit mixture models, but there are no native commands to do so. There are some user written commands that you could use. If you search for fmm you'll find one example in the SSC archives that does this.

Thanks for your reply, Sir. However, when I searched for fmm in SSC archives, I only found package for finite mixture model, not for factor mixture model. Would you please send me the link if there are commands for FACTOR mixture model. Many thanks!

[wbuchanan]

Celia Shi I stand by my previous answer. Further more, from page 153 of the most recent Mplus user's guide :

"Mixture modeling refers to modeling with categorical latent variables that represent subpopulations where population membership is not known but is inferred from the data. This is referred to as finite mixture modeling in statistics (McLachlan & Peel, 2000)" [emphasis added]

As you can see, what you asked for previously was finite mixture modeling. If, however, you wanted something else, you would need to be more specific. There are other user written commands that provide limited categorical latent variable modeling options, but based on your broad question there is no way to answer it completely.