Date:         Fri, 31 Jul 2009 11:02:50 -0400
Reply-To:     "Finegold, Kenneth" <KFinegold@URBAN.ORG>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Finegold, Kenneth" <KFinegold@URBAN.ORG>
Subject:      SURVEYLOGISTIC Odds Ratios
Content-Type: text/plain; charset="iso-8859-1"

Is there a way to produce SURVEYLOGISTIC Odds Ratios that are relative to
the grand mean?  Effect, GLM, and Reference coding all produce Odds Ratios
that are expressed in relation to one reference category for each of the
categorical variables named in the CLASS statement.

Kenneth Finegold 
Senior Research Associate 
Income and Benefits Policy

The Urban Institute 
2100 M St., NW 
Washington, DC   20037

(202) 261-5339 (phone) 
(202) 833-4388 (fax) 
kfinegol@ui.urban.org 
http://www.urban.org <thismessage:/>