Non-linear GMM PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Michael Busseri posted on Saturday, February 03, 2018 - 9:10 am
I am hoping to run a growth mixture model with three classes in which (1) the intercept and slope factors, along with their variances, are all freely estimated and not constrained to equality across classes; and (2) one of the loadings on the latent growth factor is freely estimated in each class and not constrained across classes. With respect to issue (1), I believe the following MODEL specifications will take care of the first set of requirements:

MODEL:
%OVERALL%
i s | W1RS@0 W2RS W3RS@1;
%c#1%
i s;
%c#2%
i s;
%c#3%
i s;

With respect to issue (2), however, I am uncertain as to how to freely estimate the middle loading in the growth factor within and between classes (i.e., unconstrained to equality across classes).
 Bengt O. Muthen posted on Saturday, February 03, 2018 - 2:14 pm
You can try

s BY W2RS*;

Check in Tech1 that you get what you want.
 Michael Busseri posted on Monday, February 05, 2018 - 7:12 am
Excellent. Thank you for the quick response. Your suggested approach provides exactly what I was looking for from the analysis.
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: