3-step specification LTA and distal o... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Joćo Miguel Picoito posted on Tuesday, August 27, 2019 - 2:03 pm
I am performing a latent transition mixture model using the three-step specification (as in Nylund Gibson, Grimm, Quirk and Furlong 2014).

I have so far achieved to include covariates in the LTA model, but I am having trouble including continuous and categorical distal outcomes in the model.

Do you have any example of syntax that I can use?

Is the following code correct for the distal outcome (DISTAL)?

VARIABLE:
NAMES= ind11 ind12 ind13 ind14 ind15 ind16
Ind21 ind22 ind34 ind24 ind25 ind26
Ind31 ind32 ind33 ind34 ind35 ind36
cov1 cov2 cov3 cov4
DISTAL
cl_3y cl_5y cl_7y
x2 x3 x3;

nominal=cl_3y cl_5y cl_7y;
usevar= ind-cl_7y;
CLASSES = C1(4) C2(4) C3(4);

ANALYSIS:
TYPE IS MIXTURE;
MODEL:
%OVERALL%
C2 on C1;
C3 on C1;
C1 on cov1 cov2 cov3 cov4;
C2 on cov1 cov2 cov3 cov4;
C3 on cov1 cov2 cov3 cov4;

MODEL C1:
(...)
MODEL C3:
%C3#1%
[cl_7y#1@13.059];
[cl_7y#2@10.139];
[cl_7y#3@10.118];
[DISTAL];
DISTAL;

%C3#2%
[cl_7y#1@-2.691];
[cl_7y#2@1.766];
[cl_7y#3@-1.356];
[DISTAL];
DISTAL;
(...)

Thanks in advance!
 Bengt O. Muthen posted on Wednesday, August 28, 2019 - 3:30 pm
Let's see if the authors have something to say about this.
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: