|
Dear Jim,
I have never faced problems with estimation of interaction effects in
the MIXED procedure. I do it like this, where 'z1' interacts with 'x2':
MIXED
y WITH x1 x2 z1
/FIXED = intercept x1 x2 z1 x2*z1
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/RANDOM INTERCEPT x2 | SUBJECT(CLASSID) COVTYPE(UN).
Best,
Henrik
At 19:25 22-11-2005, Jim Coan wrote:
>Dear group,
>
>I am trying to estimate effect sizes from interaction effects in SPSS's
>linear mixed model module. The software doesn't appear to be capable of
>this. Has anyone else faced this problem, and come up with a solution?
>
>Jim Coan
>
>--
>
>Jim Coan
>Assistant Professor
>University of Virginia
>Department of Psychology
>102 Gilmer Hall
>PO BOX 400400
>Charlottesville, VA 22904-4400
>TEL: 434.243.2322
>Email: jcoan@virginia.edu
>Web: http://www.people.virginia.edu/~jac3zt/
***********************************************************
Henrik Lolle
Associate Professor
Department of Economics, Politics and Public Administration
Aalborg University
Fibigerstraede 1
DK 9220 Aalborg East
http://www.socsci.auc.dk/institut2/dansk/empl/lolle.htm
***********************************************************
| 
