Dear Monir, perhaps the join count statistic for k coloured factors in the spdep package is a possibility.
best regards marco > Message: 2 > Date: Mon, 31 Aug 2009 08:26:43 -0500 > From: "Hossain, Md Monir" <monir.hoss...@uth.tmc.edu> > Subject: [R-sig-Geo] Spatial correlation for nominal variable > To: "r-sig-geo@stat.math.ethz.ch" <r-sig-geo@stat.math.ethz.ch> > Message-ID: > <fe012fdb2e167148a07cbde554b3f3a1093dcf0...@uthcms2.uthouston.edu> > Content-Type: text/plain > > Dear all, > I would appreciate much for sharing your thoughts in regard to spatial > correlation for nominal variable. > I have a variable named FP_Pattern for FringerPrint Pattern Designation > for IS6110 to indicate genotype. This is a nominal variable and has 17 > levels. For each TB patient, I also have longitude and latitude. The purpose > of > analyzing this data is to answer the question whether for given level of > genotype is there any spatial correlation. > > Thanks in advance for your time, > > Monir > -- Jetzt kostenlos herunterladen: Internet Explorer 8 und Mozilla Firefox 3 - sicherer, schneller und einfacher! http://portal.gmx.net/de/go/atbrowser _______________________________________________ R-sig-Geo mailing list R-sig-Geo@stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo