[R-sig-Geo] question on spatial bootstrap /Jackknife ......etc

Jose A. Hernandez jahernan at umn.edu
Wed Apr 5 21:40:56 CEST 2006


Dear zhijie,

zhijie zhang wrote:
> Dear firends,
>   I have two questions about spatial statistics:
> 1. As we all know ,we can calculate Moran's I to evaluate the spatial
> autocorrelation and we can also visually assess the spatial autocorrelation
> through the Variogram in Geostatistics, Now my curiosity is what is the
> difference between the two methods? Is there any relationships between them?
> I am confused by them recently?

In simple terms, Moran's I is used with lattice data and variograms are 
used for geostatistical data. In a nutshell it all depends on what type 
of data you are working with and the assumptions that you ought to comply.

On regards of the relationships and differences of the methods I would 
recommend you to look for some books on "Applied Spatial Statistics" in 
your library.

> 
> 2. How to perform spatial bootstrap /Jackknife in R? which package can be
> used?

I know that the package gstat in R does leave-one-out crossvalidation 
kriging (krige.cv), this may be what you are looking for in terms of the 
jackknife. Edzer may correct me on this one...

Good luck,

Jose

> 
>   Any suggestions are welcome. Thanks in advance!
> 
> --
> Kind Regards,Zhi Jie,Zhang ,PHDDepartment of EpidemiologySchool of Public
> HealthFudan UniversityTel:86-21-54237149
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 

-- 
Jose A. Hernandez
Precision Agriculture Center
Department of Soil, Water, and Climate
University of Minnesota
1991 Upper Buford Circle
St. Paul, MN 55108

Ph. +1 (612) 625-0445, Fax. +1 (612) 625-2208




More information about the R-sig-Geo mailing list