Geostatistics packages on CRAN

Geostatistics packages are intended for use where the variable of interest can be assumed to be continuous in (geographical) space, with the exception of regions where measurement is impossible - for example no soil samples can be taken on bedrock.

Spatial data analysis
R spatial projects

Packages on CRAN
Maps
Point pattern
Geostatistics
Areal
GIS interfaces
Others

Other Packages
Details

Mailing list
R-sig-Geo

Links
Back to GeoDa Center

gstat

gstat
has an established reputation as a stand-alone application, and has now
been developed as an R package. The Gstat project has a homepage, from which further information may be gathered; it was presentedin a paper
at DSC2003, and the published reference is: Pebesma, E. J. and
Wesseling, C. G. (1998) Gstat: a program for geostatistical modelling,
prediction and simulation. Computers and Geosciences 24, 17-31. The gstat package is described in "Multivariable geostatistics in S: the gstat package" by Edzer Pebesma, Computers and Geosciences 30 (7), pp. 683-691.

geoR and geoRglm

geoR, and the associated geoRglm, implement model-based geostatistics. geoR has a homepage, as does geoRglm. They were presented in two notes in R News:

• Paulo J. Ribeiro, Jr. and Peter J. Diggle. geoR: A package for geostatistical analysis. R News, 1(2):15-18, June 2001.
• Ole F. Christensen and Paulo J. Ribeiro. georglm: A package for generalised linear spatial models. R News, 2(2):26-28, June 2002.

and in a paper at DSC2003.

spatial

The VR bundle includes the spatial package, which has recommended status, and is thus available in every R installation. The functions are documented in: William N. Venables and Brian D. Ripley. Modern Applied Statistics with S. Fourth Edition. Springer, 2002. They include variogram/correlogram functions, surf.ls() and surf.gls() for trend surfaces and kriging, and prediction functions.

fields

fields is a larger package, with a well-resourced homepage. It is a collection of programs for curve and function fitting with an emphasis on spatial data and spatial statistics. The major methods implemented include cubic and thin plate splines, universal Kriging and Kriging for large data sets. One main feature is any covariance function implemented in R can be used for spatial prediction.

RandomFields

RandomFields was presented in an R News note:

• Martin Schlather. Simulation and analysis of random fields. R News, 1(2):18-20, June 2001.

and has a detailed homepage.

sgeostat

sgeostat was written for S, and is documented in a homepage.
It was ported to R by Albrecht Gebhardt, and should be used with the
tripack package, which he also ported. The akima package for spline
interpolation for irregular gridded data, also ported by Albrecht
Gebhardt, dates from the same period.

vardiag

vardiag is a package for interactive variogram diagnostics; details were given in a DSC2003 paper.