Three-level-Interaction in Multilevel... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Cosma Hoffmann posted on Thursday, July 16, 2020 - 4:38 am
Hi,

I have a quastion because I never found a model like this:
Is it possible that two predictors on L2 (in my case personality
traits of persons) can interact in predicting a random slope
on L1 (states of negative affect on stress)?

I thought it should look like this:

USEVARIABLES = Stress NA Trait1 Trait2 INT;

WITHIN = Stress;
BETWEEN = Trait1 Trait2;
DEFINE:
INT = Trait1*Trait2;

analysis: type = twolevel;

MODEL:
%WITHIN%
Slope| NA ON Stress;

%BETWEEN%
Slope ON Trait1 Trait2 INT;

If it is possible, how can I model this and probe such an
interaction?
And is it necessary to center the predictors?

Kind regards Cosma
 Bengt O. Muthen posted on Friday, July 17, 2020 - 6:04 pm
Yes, this is possible. You have to also put Int on the Between list. You probe this between-level regression just like you do an ordinary regression with interaction.
 Cosma Hoffmann posted on Saturday, July 25, 2020 - 6:14 am
Thank you for ur answer!
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: