The codispersion coefficient quantifies the association between two spatial
processes for a particular direction (spatial lag) on the two-dimensional
space. Following R code reflects the computational
procedure to estimate the values of the codispersion and the plotting procedure
to yield the codispersion map. This code also is available as an R source file:
codismap.R

Source:
Vallejos, R., Osorio, F., Mancilla, D. (2015).
The codispersion map: a graphical tool to visualize the association between two spatial variables.
Statistica Neerlandica 69, 298-314.

Codispersion map for rectangular grids

The R function hcodisp.map provides a graphical
tool called codispersion map to visualize the spatial correlation between
two sequences measured for regular lattices on the plane. Sources for this
codispersion map are available at the next link:

To use this funtion, first download the source as a tarball (.tar.gz) file.
Unpack the tarball (thereby creating a directory named, hcodisp.map) and to
create the Dynamically Loaded (DL) library, enter at the console prompt:

To use this funtion, start R and enter:

Source:
Vallejos, R., Osorio, F., Mancilla, D. (2015).
The codispersion map: a graphical tool to visualize the association between two spatial variables.
Statistica Neerlandica 69, 298-314.

Codispersion map using kernel estimation

Codispersion map between two spatial processes using a nonparametric approach.
An R script and the source for the computatioon of the codispersion coefficient
are available at: codisp.kern_script.R
and codisp.kern.R
, respectively.

Function to compute the codispersion coefficient between two spatial processes.
The routine uses geodata objects (from geoR package):

Source:
Cuevas, F., Porcu, E., Vallejos, R. (2013).
Study of spatial relationships between two sets of variables: A nonparametric approach.
Journal of Nonparametric Statistics 25, 695-714.