Date: Mon, 19 Apr 2004 18:07:10 +0200
ReplyTo: MOSER Winfried <winfried.moser@statistik.gv.at>
Sender: "SPSSX(r) Discussion" <SPSSXL@LISTSERV.UGA.EDU>
From: MOSER Winfried <winfried.moser@statistik.gv.at>
Subject: PhiCoefficient
ContentType: text/plain; charset="USASCII"
Dear List!
I need to "scan" a database with many, mostly nominal Variables, for
contingencies.
Is there a possibility to produce a matrix, which shows me the
phicoefficients (or other measures for nominal variables) of all
possible combinations of variables, (something like the outputmatrix of
the procedure for bivariate correlations).
thanks in advance
Winfried
