Moderation in actor-partner-independe... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
 Isabelle Lichy posted on Thursday, January 28, 2016 - 6:56 am

I need to make a moderation analysis in Mplus within the actor partner independence model but have no clue how to include a moderator variable (humor frequency) in the regression of SAM (stress level) ON Pos_m/Pos_w (Positive Humor).

Find the current syntax below. Can anybody help?

posw = CLUSTER_MEAN(Pos_w);

CENTER day Pos_m Pos_w (GROUPMEAN);

VARIABLE: NAMES ARE cluster day Pos_m Pos_w
SAM_f_m SAM_f_w SAM_a_m SAM_a_w;


USEVARIABLES = cluster day Pos_m Pos_w SAM_a_m SAM_a_w posm posw;

BETWEEN = posm posw;
WITHIN = day Pos_m Pos_w;
CLUSTER = cluster;

ANALYSIS: TYPE = twolevel random;



ind_m | SAM_a_m ON Pos_m;
ind_w | SAM_a_w ON Pos_w;
cross_mw | SAM_a_w ON Pos_m;
cross_wm | SAM_a_m ON POs_w;

SAM_a_m SAM_a_w ON day;
SAM_a_m WITH SAM_a_w;

SAM_a_m ON posm posw;
SAM_a_w ON posm posw;

SAM_a_m WITH SAM_a_w ind_m ind_w cross_mw cross_wm;
SAM_a_w WITH ind_m ind_w cross_mw cross_wm;
ind_m WITH ind_w cross_mw cross_wm;
ind_w WITH cross_mw cross_wm;
cross_mw WITH cross_wm;

sampstat CINTERVAL;
 Bengt O. Muthen posted on Thursday, January 28, 2016 - 6:29 pm
For moderation - in the form of a cross-level interaction - you would have to regress your random slopes on level-2 covariates, not just the random intercepts as you do now.
 Isabelle Lichy posted on Thursday, January 28, 2016 - 7:08 pm
Thank you for your reply!!

Could you show me this within the Syntax?

Or is there any example given in form of a syntax like I have found for the basic APIM?
 Bengt O. Muthen posted on Friday, January 29, 2016 - 6:03 pm
See the section on Cross-level Interaction on our Mediation page:
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