How to correct my growth model for age? PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Miriam Haaksma posted on Wednesday, September 05, 2018 - 8:38 am
I have built a quadratic growth model for cognition across 4 time points, with random intercept and slope in two different cohorts and now I would like to compare the trajectories across these two cohorts. In order to make a fair comparison, I want to correct the intercept and slope of my models for age (centered on 65: agec). In order to do this, I have added the following to my model statement:

agec on mi;
agec on ms;
agec@0;

And this is part of my output:

AGEC ON
MI -10.201 3.500 -2.914 0.004
MS 17.354 5.990 2.897 0.004

(...)

Intercepts
M0 0.000 0.000 999.000 999.000
M1 0.000 0.000 999.000 999.000
M2 0.000 0.000 999.000 999.000
M3 0.000 0.000 999.000 999.000
AGEC 255.896 84.559 3.026 0.002

These are my questions:

1) what does the intercept of agec (255.896) in the output mean? It is counted as a parameter in the model, but I don't understand what it represents.

2) Should I remove this "intercept age" parameter? If yes, how can I do that?
 Bengt O. Muthen posted on Thursday, September 06, 2018 - 2:58 pm
I assume that MI and MS are the intercept and slope. I think you may have the ON statement backwards - perhaps you mean to instead say:

MI MS ON Agec;

ON means regressed on. What is on the right-hand side of ON is what influences what's on the left.
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: