[R] re: Spatial stats: R vs. Splus

[José Ernesto Jardim]

Kenneth Nordstrom wrote:

> Hello,
>
> Could someone tell me whether the spatial statistics module of
> Splus is worth the rather high price, or whether one could (with
> reasonable effort) carry out the same things using R and some of
> its contributed packages.
>
> Although we do have Splus (Windows and Unix), we definitely prefer
> to use R whenever feasible (both for research and teaching).
>
> Thanks for developing a superb computing/programming environment.
>
> Kenneth Nordström
>
> ......................................................................
>
> Kenneth Nordström                      Kenneth.Nordstrom at oulu.fi
> Professor of Statistics
> Head of Statistics Division
> Dept of Math Sciences                  Tel: +358-8-553 1829
> Univ of Oulu                                +358-8-553 1820 (secr)
> P.O. Box 3000                          Fax: +358-8-553 1848
> FIN-90014 Univ of Oulu
> FINLAND                                http://stat.oulu.fi/nordstrom/
>
> ......................................................................
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

Hi

The packages referred by Paulo are very good and you can do most of the things
that S+SS do, and some that it doesn't. Like cross-variograms and co-kriging, or
the non-gaussian kriging proposed by Paulo in geoR using MCMC and Bayes stats.
Also geoR has very good exploratory data analysis functions and Sgeostat is very
good for variogram analysis.

However there's something you can't do with the R packages, the variogram using
tolerance for angle and lags at the same time. I mean, the variogram function of
S+SS is more flexible then the one's you get on R, and if you're dealing with
irregular grided data that is very important.

If this problem could be solved there would be no need to by S+SS ...

I'm a very poor developer but I'm available to help if someone decides to develop
a good and flexible variogram function.

Regards

EJ


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._