Latent transition analysis (LTA) with... PreviousNext
Mplus Discussion > Categorical Data Modeling >
 Jennifer Yahner posted on Thursday, September 23, 2010 - 12:56 pm

Could someone please confirm that -- in the context of conducting a latent transition analysis (e.g., example 8.13) -- it is okay to add additional regression equations to the MODEL, so as to estimate the effect of a mediator M of X's effect on C1 and C2 classes?

I physically tested this in Mplus and received no error messages, but want to confirm it's okay since I see no solid instance of it being done.

Also, if you can point me to any references showing mediation in LTA using Mplus, I would be very grateful!

 Linda K. Muthen posted on Thursday, September 23, 2010 - 2:35 pm
Yes, this is okay.

Perhaps the Nylund dissertation on the website deals with this.
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