variogmultiv: Function to compute multivariate empirical variogram

In adespatial: Multivariate Multiscale Spatial Analysis

Function to compute multivariate empirical variogram

Description

Compute a multivariate empirical variogram. It is strictly equivalent to summing univariate variograms

Usage

variogmultiv(Y, xy, dmin = 0, dmax = max(dist(xy)), nclass = 20)

Arguments

Y	A matrix with numeric data
xy	A matrix with coordinates of samples
dmin	The minimum distance value at which the variogram is computed (i.e. lower bound of the first class)
dmax	The maximum distance value at which the variogram is computed (i.e. higher bound of the last class)
nclass	Number of classes of distances

Value

A list:

d	Distances (i.e. centers of distance classes).
var	Empirical semi-variances.
n.w	Number of connections between samples for a given distance.
n.c	Number of samples used for the computation of the variogram.
dclass	Character vector with the names of the distance classes.

Author(s)

Stéphane Dray [e-mail]

References

Wagner H. H. (2003) Spatial covariance in plant communities: integrating ordination, geostatistics, and variance testing. Ecology, 84, 1045–1057

Examples

if(require(ade4)){
data(oribatid)
# Hellinger transformation
fau <- sqrt(oribatid$fau / outer(apply(oribatid$fau, 1, sum), rep(1, ncol(oribatid$fau)), "*"))
# Removing linear effect
faudt <- resid(lm(as.matrix(fau) ~ as.matrix(oribatid$xy))) 
mvspec <- variogmultiv(faudt, oribatid$xy, nclass = 20)
mvspec
plot(mvspec$d, mvspec$var,type = 'b', pch = 20, xlab = "Distance", ylab = "C(distance)")
}

adespatial documentation built on Oct. 19, 2023, 1:06 a.m.