Date:         Thu, 1 Sep 2005 07:18:15 -0400
Reply-To:     "David M. Fresco" <fresco@kent.edu>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "David M. Fresco" <fresco@kent.edu>
Subject:      Decomposing interaction term in Cox Regression
In-Reply-To:  <20050901050233.BE67E5790EA@smtp.kent.edu>
Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed

Colleagues:

I am hoping for some help in undertaking a decomposition of an
interaction effect in Cox regression.

I am tracking when relapse occurs in a sample of individuals as a
function of what treatment they received as well as two additional
factors A, B and A*B.

The output indicates that the interaction of A*B is significant and a
get a B and SE of B in the output.  I am certainly familiar with
solving interactions for OLS, but would welcome some suggestions on
how to interpret this interaction.

Below is essentially the syntax I used.


COXREG  relapse
   /STATUS=censored(0)
   /STRATA = txcond
   /METHOD=ENTER a  /METHOD=ENTER b /method = ENTER a*b
   /CRITERIA=PIN(.05) POUT(.10) ITERATE(20) .

Thanks in advance and I would appreciate my email being cc'ed to
responses as I take the digest.

------
David M. Fresco, Ph.D.               fresco@kent.edu
Department of Psychology        Voice:  (330) 672-4049
Kent State University                   Fax:    (330) 672-3786
226 Kent Hall Annex
P.O. Box 5190                               http://dept.kent.edu/
psychology/
Kent, OH  44242-0001                http://www.personal.kent.edu/
~dfresco/

ListOwner of Helplessness http://psych.upenn.edu/~fresco/
helplessness.html
Listowner of Mindfulness http://listserv.kent.edu/archives/
mindfulness.html