Bidirectional model with 1 occasion m... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Djuke Brinksma posted on Thursday, June 02, 2016 - 2:16 am
I want to make a bidirectional model of 3 variables (A, B and C) of which 1 is only measured twice: lets assume A is modeled twice at T1 and T3 and B and C are measured all 3 times. Is it possible to model this, or will this model be unstable? I'm especially worried about the following crosslagged pahts:

A1 --> C3 OR B1 --> A3
A1 --> A3

Or is it better to only take the paths at the following occasion (from 1 to 2 and avoid paths from 1 to 3)
 Linda K. Muthen posted on Thursday, June 02, 2016 - 1:41 pm
If A is not measured at time point 2, there is no variable A at that time point. The data set would be

A1 A3 B1 B2 B3 C1 C2 C3

You can model the above variables. It looks like you don't have A2 in the model above.
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: