|
Message/Author |
|
|
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? |
|
|
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 |
|
|