Variogram.corSpatial {nlme}R Documentation

Calculate Semi-variogram for a corSpatial Object

Description

This method function calculates the semi-variogram values corresponding to the model defined in FUN, using the estimated coefficients corresponding to object, at the distances defined by distance.

Usage

## S3 method for class 'corSpatial':
Variogram(object, distance, sig2, length.out, FUN, ...)

Arguments

object an object inheriting from class corSpatial, representing spatial correlation structure.
distance an optional numeric vector with the distances at which the semi-variogram is to be calculated. Defaults to NULL, in which case a sequence of length length.out between the minimum and maximum values of getCovariate(object) is used.
sig2 an optional numeric value representing the process variance. Defaults to 1.
length.out an optional integer specifying the length of the sequence of distances to be used for calculating the semi-variogram, when distance = NULL. Defaults to 50.
FUN a function of two arguments, the distance and the range corresponding to object, specifying the semi-variogram model.
... some methods for this generic require additional arguments. None are used in this method.

Value

a data frame with columns variog and dist representing, respectively, the semi-variogram values and the corresponding distances. The returned value inherits from class Variogram.

Author(s)

Jose Pinheiro Jose.Pinheiro@pharma.novartis.com and Douglas Bates bates@stat.wisc.edu

References

Cressie, N.A.C. (1993), "Statistics for Spatial Data", J. Wiley & Sons.

See Also

corSpatial, Variogram.default, Variogram.corExp, Variogram.corGaus, Variogram.corLin, Variogram.corRatio, Variogram.corSpher, plot.Variogram

Examples

cs1 <- corExp(3, form = ~ Time | Rat)
cs1 <- Initialize(cs1, BodyWeight)
Variogram(cs1, FUN = function(x, y) (1 - exp(-x/y)))[1:10,]

[Package nlme version 3.1-66 Index]