Last 3 Days
Mediated effects of slope
Growth Modeling of Longitudinal Data
posted on Tuesday, June 03, 2014 - 3:17 pm
I am trying to model post traumatic growth as function of trauma exposure mediated by positive coping styles.
I had hope to estimate mean level change in the growth variables by estimating s | PT1 PTG2
then testing the s IND coping trauma
But I see that model indirect cannot be used with TYPE=RANDOM
What is the best way to examine the mediated effects of x via m on change in y?
Bengt O. Muthen
posted on Tuesday, June 03, 2014 - 5:50 pm
A growth model such as
i s |
does not need TYPE=RANDOM.
Also, any indirect effect can be computed in Model Constraint as
indir = a*b;
where a is coping on trauma and b is s on coping.
Back to top
Add Your Message Here
This is a private posting area. Only registered users and moderators may post messages here.
Enable HTML code in message
Automatically activate URLs in message