Starting values for Growth Mixtures PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Nidhi Kohli posted on Friday, November 09, 2012 - 3:22 pm

I want to understand how Mplus will choose starting values to fit a growth mixture model, if the user does not provide any starting values.


 Tihomir Asparouhov posted on Friday, November 09, 2012 - 8:49 pm
The starting values are the same across the classes. The means for the growth factors are obtained from the regular regression of the dependent variables on the time scores. The covariances are started at 0. The variance are started at the variance of the individual row regression coefficients on the time scores.
 Nidhi Kohli posted on Saturday, November 10, 2012 - 5:52 am
Thanks! This is helpful.
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