Specifying a second order curve model PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
 Mark A Serva posted on Monday, September 13, 2010 - 8:25 am
I am fairly new to growth curve modeling, and have a question regarding the configuration of the model.

I am running a growth curve model with four first order latent constructs (computer anxiety for t1, t2, t3, and t4). The second order factors are of course the slope and intercept.

In the output, the mean for the intercept is listed as 0 (and presumably has been fixed to this value). In my earlier models where the trajectory parameters are the first order factors, this value was always non-zero and highly significant (which makes sense, given its meaning on the survey).

My question is whether or not I should free the mean for the intercept, and if so, how to do so?

Thank you.
 Linda K. Muthen posted on Monday, September 13, 2010 - 9:38 am
For multiple indicator growth, we use the parametrization where intercepts are held equal across time and the mean of the intercept growth factor is fixed at zero. See the Topic 4 course handout under multiple indicator growth to see the steps and model we recommend in this case.
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