On Mon, 12 Mar 2007 [EMAIL PROTECTED] wrote:

> I am trying to determine how to evaluate homogeneity of points in 
> three-dimensional space.
> 
> In two-dimensional data, I have used functions available in the Spatial 
> package
>         and I've have looked into the spatstat package
>         but, as far as I can tell, neither appears to handle 3-dimensional 
> data.
> 
> Is there another version, package, or software that does the same type 
> (G-function, etc.) of evaluation for 3-D data?

I believe that you are correct with regard to spatial, spatstat, and 
splancs. For G, it would be possible to get most of the way there using an 
off-CRAN package interfacing David Mount's Approximate Nearest Neighbours 
code that I can make available (depending on your platform), substantially 
improved thanks to Christian Sangiorgio.

> set.seed(1)
> library(ann)
> D3 <- matrix(runif(3000), ncol=3) 
> res <- ann(D3)$dnn
> quantile(res, seq(0,1,1/10))
> plot(ecdf(res))

The real difficulties would start with edge adjustment, sampling within a 
volume for simulation ought to be OK, at least for a cube.

Roger

> 
> Thanks sincerely,
>  Tom Filloon   [Procter & Gamble, Cincinnati, Ohio USA]
> 
> 
> 
>       [[alternative HTML version deleted]]
> 
> ______________________________________________
> [email protected] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 

-- 
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]

______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Reply via email to