Predictors on intercept and slope PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Corinna posted on Tuesday, September 15, 2015 - 12:14 pm
Dear Linda & Bengt,
I am calculating an LCGA with 4 classes and several predictors. I would like to get class specific influences of the predictors on intercept and slope. Is it possible to specify that in the Mplus syntax? Until now the influence of the predictors on the growth factors is hold constant (the same) across the classes. But I would like to know which influence a specific predictor has on i and s in a specific class?!

Thank you very much,
kind regards,
Corinna
 Linda K. Muthen posted on Tuesday, September 15, 2015 - 12:21 pm
You can relax the default equality by mentioning the ON statements in the class-specific part of the MODEL command.
 Corinna posted on Tuesday, September 15, 2015 - 1:52 pm
Thank you very much. I tried this but I get an error. Is this because I have an LCGA with fixed variances of i and s? Here is my syntax:

variable: names = age KST1 KST2 KST3 KST4 EKS Dep LEw1 SC SB Klim mig id;
auxiliary = id;
usevar = KST1 KST2 KST3 KST4 EKS Dep LEw1 SC SB Klim mig;
missing = all(9999);
classes= c(2);
analysis: type = MIXTURE;
STARTS = 1200 400;
model: %OVERALL%
i s q|KST1@0 KST2@1 KST3@2 KST4@3;
i s q on EKS Dep LEw1 SC SB Klim mig;
c on EKS Dep LEw1 SC SB Klim mig;

%c#1%
i@0;
s@0;
q@0;
i s q on EKS Dep LEw1 SC SB Klim mig;
c on EKS Dep LEw1 SC SB Klim mig;
KST1; KST2; KST3; KST4;

%c#2%
i@0;
s@0;
q@0;
i s q on EKS Dep LEw1 SC SB Klim mig;
c on EKS Dep LEw1 SC SB Klim mig;
KST1; KST2; KST3; KST4;

Thank you very much.
 Linda K. Muthen posted on Tuesday, September 15, 2015 - 7:42 pm
Please send the full output and your license number to support@statmodel.com.
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: