3 level complex and longitudinal data PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
 Wen-Hsu Lin posted on Thursday, September 26, 2013 - 7:40 am
I have a data set that I want to see how class atmosphere influences students' depression.My question is that how do I model this when the cluster covariate also measured at three time points as the individual level outcome variable (depression). Also, I have individual level covariates (e.g., family cohesion). Thank you.

Depression: measured at three time point
Class atmosphere: measured at three time point
 Bengt O. Muthen posted on Thursday, September 26, 2013 - 8:21 am
It sounds like you have a time-varying covariate (class atmosphere) on the between level of the growth model. That can be included in a setup such as UG ex 9.12.
 Wen-Hsu Lin posted on Thursday, September 26, 2013 - 7:47 pm
Thank you so much Dr./Prof. B. Muthen. Continue on this issue. I have two further questions
(1)In UG ex 9.12, do I specify the third level time-varying variable to influence y1-y4?
(2)I am thinking that create a between model growth curve, which influence on the withing model growth curve.
In other words, similar to UG ex. 9-12, I replace the effect of w on ib sb by another two growth curve latent variables (say i b).
Is it feasible?

Thanks a lot.
 Bengt O. Muthen posted on Friday, September 27, 2013 - 8:57 am
1.Yes, on Between.
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