[R-sig-Geo] correlogram for categorical data

[White.Denis at epamail.epa.gov]

Yes, a "joincountogram" is the idea.  Thanks for advice on size, I'll
try scaling up.


Roger Bivand <Roger.Bivand at nhh.no> wrote on 2006-10-19 00:05:31:

> On Wed, 18 Oct 2006 White.Denis at epamail.epa.gov 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 at 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: Roger.Bivand at nhh.no
>