Simulating Two Surfaces with a user-defined Cross-Correlation Index
If the variables are spatially uncorrelated, it is a special case of what I provided, and you could specify the variography in terms of pure nuggets, and/or use a neighbourhood of 1 (or 0?). As an alternative, fill the grids with data generated with function rmvnorm in package mvtnorm. I find it however hard to understand what you mean by a spatial cross-correlation index, especially the word spatial, when you do not want to address spatial autocorrelation of the variables themselves. -- Edzer
Enrico R. Crema wrote:
Many Thanks, But I guess explained very badly (sorry for this!!) what I need. I am building an Agent Based Simulation and part of the model requires series of two randomly generated raster maps, having a spatial cross-correlation index ranging from -1 to +1. Clearly If I can specify autocorrelation of each that will be even better, but at this stage I just need two randomly generated surfaces with a user-specified Cross-Correlation Index. Sorry again for the bad explanation! Enrico --------------------------------------- Enrico R. Crema PhD Candidate Institute of Archaeology, UCL AHRC Centre for the Evolution of Cultural Diversity, UCL http://www.cecd.ucl.ac.uk/people/?go1=91 +44 7899093191 e.crema at ucl.ac.uk enrico.crema at gmail.com On 9 Oct 2009, at 07:49, Edzer Pebesma wrote:
Enrico, try library(gstat) demo(cosimulation) First part is on Gaussian simulation, the second on indicator simulations. Best regards, Enrico R. Crema wrote:
Dear All, Is there any R function capable a set of two raster maps with a user- defined spatial cross-correlation index (between the two rasters)? Many Thanks, Enrico Crema --------------------------------------- Enrico R. Crema PhD Candidate Institute of Archaeology, UCL AHRC Centre for the Evolution of Cultural Diversity, UCL http://www.cecd.ucl.ac.uk/people/?go1=91 +44 7899093191 e.crema at ucl.ac.uk enrico.crema at gmail.com [[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
-- Edzer Pebesma Institute for Geoinformatics (ifgi), University of M?nster Weseler Stra?e 253, 48151 M?nster, Germany. Phone: +49 251 8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de/ http://www.springer.com/978-0-387-78170-9 e.pebesma at wwu.de
Edzer Pebesma Institute for Geoinformatics (ifgi), University of M?nster Weseler Stra?e 253, 48151 M?nster, Germany. Phone: +49 251 8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de/ http://www.springer.com/978-0-387-78170-9 e.pebesma at wwu.de