Multigroup moderation PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Djuke Brinksma posted on Wednesday, May 31, 2017 - 1:36 am
I want to examine a path analyses where X (cat) predicts Y (cat) moderated by (M) and to see whether there are differences across 2 groups (G).

First, I want to test the moderation without the groups by creating a new variable XM which will than contain 6 groups. Can I use chi-square difference test to see whether there is moderation?

Second, I want to see whether the model from the first step differs across 2 groups by using chi-square differences again and than using wald-test for the specific paths.

Is my analytic approach ok?
 Bengt O. Muthen posted on Wednesday, May 31, 2017 - 5:45 pm
Q1: Just see if XM has a significant effect. There is more on this topic in our new book.

Q2: I would suggest using the Wald test (Model Test)
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: