Conditional Mean (Intercept & Slope)... PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Tom Hildebrandt posted on Saturday, November 17, 2007 - 3:16 am
1) Is there a way to request the slope means in a LGCM for each level of a covariate or do these have to be hand calculated from the output.

2) A related question would be how to get the model estimated means for two treatments in a LGCM? I seem only to be able to get the estimated means for the entire sample, but want to look at the differences for each treatment at each time point. Is this possible in Mplus?

3) Could anyone recomended a reference for calculating effect sizes for covariates (e.g., tx) in a LGCM?

Thanks in advance advance!
Tom
 Bengt O. Muthen posted on Saturday, November 17, 2007 - 12:21 pm
1) You can use Model Constraint and define "NEW" parameters, such as

smean1 = a + b*1;
smean2 = a + b*2;

where a is your slope intercept, b is your slope's regression coefficient on x, and 1 and 2 are the x covariate values. The NEW parameters will get estimates and SEs.

2) Use Model Constraint.

3) Muthen-Curran (1997) talks about it - anyone else?
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: