[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-geo
Subject:    Re: [R-sig-Geo] Geographically Weighted Discriminant Analysis
From:       Roger Bivand <Roger.Bivand () nhh ! no>
Date:       2008-03-26 16:05:13
Message-ID: Pine.LNX.4.64.0803261650570.11431 () reclus ! nhh ! no
[Download RAW message or body]

On Wed, 26 Mar 2008, Hisaji ONO wrote:

> Hello.
>
> I found following article.
>
> Geographically Weighted Discriminant Analysis
> Chris Brunsdon, Stewart Fotheringham, Martin
> Charlton(2007):
> Geographical Analysis, Volume 39, Issue 4, Page 376-396,
> Oct 2007
> http://www.blackwell-synergy.com/doi/abs/10.1111/j.1538-4632.2005.00633.x
>
> Can ggwr function in spgwr deal with this method?

Hi,

Not as such, no, because it uses glm(), and one would need a multinomial 
response. You could look at how multinom() in the nnet package could be 
adapted, it would easier than lda() or qda() in MASS, which do not take a 
weights= argument.

Hope this helps,

Roger

>
>
> Regards.
>
>

-- 
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@nhh.no

_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
[prev in list] [next in list] [prev in thread] [next in thread]