Covariates in LCGA PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 N_2018 posted on Friday, July 21, 2017 - 12:44 pm
I would like to conduct a latent class growth analysis with covariates and have a few questions.

My model (for reference):
i s q u | im13@0 im14@1 im15@2 im16@3 im17@4 im18@5 im19@6 im20@7;
i-u ON iq ses black hisp other;
c#1 ON iq ses black hisp other;
c#2 ON iq ses black hisp other;

(1) Are the commands I use to control for my covariates (iq ses black hisp other) appropriate if my goal is to adjust class membership and class slopes for these covariates?

(2) If I am interested in obtaining the estimates for each of the class slopes (e.g., determining whether the linear, quadratic, and cubic terms are significant for Class 1), would this information be located under the INTERCEPTS heading in the output?

(3) Are the plot function and 'SAVE=cprob' option offered for this type of analysis (when it includes covariates)?

(4) Can I conduct an LCGA with covariates using a negative binomial framework (i.e., when my time variables are COUNT variables)?

Thanks in advance for your time and assistance!
 Bengt O. Muthen posted on Friday, July 21, 2017 - 4:58 pm
(1) Yes.

(2) No, you should look at TECH4.

(3) Try it and see.

(4) Yes.
 Sofie Danneel posted on Monday, January 07, 2019 - 6:41 am

I was wondering if I could add covariates for the intercept and slope in an LCGA (e.g. I ON Cohort)

 Bengt O. Muthen posted on Monday, January 07, 2019 - 11:23 am
Yes, that is possible.
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