Yes, a "joincountogram" is the idea. Thanks for advice on size, I'll try scaling up.
Roger Bivand <[EMAIL PROTECTED]> wrote on 2006-10-19 00:05:31: > On Wed, 18 Oct 2006 [EMAIL PROTECTED] wrote: > > > I have a 1000 x 1000 grid of categorical values (nine of > these) and want > > to compute and plot a correlogram. Function cell2nb() > will take a while > > it appears but if that succeeds then can methods of sp. > correlogram() be > > used on categorical data? What are "style" options in > sp.correlogram()? > > > > Sorry, could you say how a correlogram might be constructed for > categorical values (eg. land cover)? Wouldn't join counts be a more > natural choice? joincoint.multi() in spdep has a Jtot > value of total > different category joins, so using that with different > lags of a cell2nb() > neighbour list might work. However, the 1M cell grid is > pretty large for > cell2nb(), using dnearneigh() on cell centres may be > faster and scale > better, (and other possibilities should exist) and nblag() will be > definitely sub-optimal in this setting. For join counts, > the "B" weights > style is the obvious one to chose. Note that joincoint. > multi() is not > coded in C. > > This would need trying on a small subset and scaling up - > I think that > alternative routes to constructing the lagged neighbour > lists would be > preferable. > > Roger > > > thanks, > > Denis > > > > _______________________________________________ > > R-sig-Geo mailing list > > R-sig-Geo@stat.math.ethz.ch > > https://stat.ethz.ch/mailman/listinfo/r-sig-geo > > > > -- > Roger Bivand > Economic Geography Section, Department of Economics, > Norwegian School of > Economics and Business Administration, Helleveien 30, N-5045 Bergen, > Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43 > e-mail: [EMAIL PROTECTED] > _______________________________________________ R-sig-Geo mailing list R-sig-Geo@stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo