[R-sig-Geo] Prediction using geoR

Paulo Justiniano Ribeiro Jr paulojus at c3sl.ufpr.br
Sat Aug 22 01:02:45 CEST 2009


Kabeli

geoR is one among several packages which performs spatial prediction via 
kriging.

The page spatial task view on CRAN provides a good overview of the 
resources

For the geoR there are a few tutorials with example code
available from the geoR Tutorial 
Section in the geoR web page at
www.leg.ufpr.br/geoR

Paulo Justiniano Ribeiro Jr
LEG (Laboratorio de Estatistica e Geoinformacao)
Universidade Federal do Parana
Caixa Postal 19.081
CEP 81.531-990
Curitiba, PR  -  Brasil
Tel: (+55) 41 3361 3573
Fax: (+55) 41 3361 3141
e-mail: paulojus AT  ufpr  br
http://www.leg.ufpr.br/~paulojus



On Fri, 21 Aug 2009, KABELI MEFANE wrote:

> Hi All
> ?
> New to the list.? I have a problem of doing of having to predict Z(so)?where so =(0.5,0.5)? assuming we have measured Z(s1)=3 at (0,0), Z(s1)=5 at (0,1), Z(s3)=6, at (1,0), Z(s4)= 4 at (1,1) ,?
> gamma(h) = h^2?????? when h<1
> ??????????????? = h???????? when h>=1
> This is a practical example i am using,
> I am workng at Lesotho Bureau of Statistics, so i am trying to learn R as fast as possible since i would like to use for analysis of data from our coming Demographic health survey to see the concentration of HIV positive people aroung our four regions. i know that i have to use kriging but i can only do that manual for this point, but its?difficult when using R. i can go as far as the coordinates and values
> ?
> ?
> ?coords.1 coords.2 data
> 1??????? 0??????? 0??? 3
> 2??????? 0??????? 1??? 5
> 3??????? 1??????? 0??? 6
> 4??????? 1??????? 1??? 4
>
>
>
>
> 	[[alternative HTML version deleted]]
>
>



More information about the R-sig-Geo mailing list