Poisson Mediation PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Steven Miller posted on Friday, October 12, 2007 - 12:53 am
I'm trying to run a model with mediation...my IV and DV are normally distributed, but my mediator is count. Is there a way to do this? I get errors when I leave my mediator as count. I've tried setting it to categorical and using theta parameterization, though this doesn't seem appropriate. The syntax follows.

Thanks in advance,
Steve

VARIABLE: NAMES ARE
totcomps bdiscont intrntot;
categorical IS totcomps;

USEVARIABLES ARE
intrntot totcomps bdiscont;
Missing = all(-1234) ;
ANALYSIS: TYPE = GENERAL MEANSTRUCTURE;
parameterization = theta;
BOOTSTRAP = 5000;

MODEL:
bdiscont ON totcomps* (p1);
bdiscont ON intrntot;

totcomps ON intrntot* (p2);
totcomps*;

[intrntot*];
intrntot*;

MODEL CONSTRAINT:
NEW(ind_effect);
ind_effect = p1*p2;

OUTPUT: CINTERVAL(bcbootstrap);
 Linda K. Muthen posted on Friday, October 12, 2007 - 12:31 pm
Please send your input, data, output, and license number to support@statmodel.com so I can see the problem you get when you have the mediator variable a count variable.
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: