Date:         Tue, 30 Nov 1999 02:26:14 +0100
Reply-To:     "Christian F.G. Schendera" <cschende@IX.URZ.UNI-HEIDELBERG.DE>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Christian F.G. Schendera" <cschende@IX.URZ.UNI-HEIDELBERG.DE>
Subject:      Q: control of covariate (ordinal data only!)
Comments: To: SASL <SAS-L@UGA.CC.UGA.EDU>
Content-Type: text/plain; charset="iso-8859-1"

hello all,
*situation: All ind. vars are binary or polytomous ordinal. The single
response var MANNAG is binary.
* observation: SEX seems to covary with MANNAG (girls have more 1s of
MANNAG, boys more 0s)
* question: If I want to analyse the effects of, say ERSTGSK, on MANNAG, how
could I control the possible effect of SEX? Neither in STAT, vol. 2 (no
wonder), nor in CaE to 6.12 I did find something related to the control of
a covariate's effect. I am unexperienced in that special kind of analysis.
Every tipp is very welcome. Thank you in advance,
Chris

* this is the code (speculative example):
proc logistic data = TEST order=data ;
model MANNAG = MOTAUF BERUFVAK ERSTGSK RISKGB2 WOHNORT / influence ;
run ;

* this is how the dataset looks like (example)
ID BERUFVAK  WOHNORT  MOTAUF  MANNAG1  ERSTGSK  KKK  RISKGB2 SEX
   1      1        2             1             0     3      0      0 0
   2      1        2             1             0     3      0      0  1
   3      2        1             0             1     3      1      1 0
   4      2        1             0             1     3      1      0 1
    5      .        2             1             0     4      0      0  1
............