covarianceFactory {GeneralizedWendland}

covarianceFactory

Description

A function factory which sets up a covariance function.

Usage

covarianceFactory(covariance, cov.args = list())

Arguments

covariance

A function which takes as input an object containing distances (h), a vector of parameters (theta), and a list of optional settings (cov.args)

cov.args

A list of optional settings for a covariance function.

Details

covarianceFactory() is a function factory which takes as input an arbitrary covariance function and a list of additional arguments and returns a function with these arguments. The argument cov.args mainly serves to pass the relevant arguments to the covariance function, but also allows users to specify the following two arguments:

cov.fixed_range_value (default: NA)

A constant value for the range parameter. Note that the code assumes that the first value of theta corresponds to the range parameter, as this notation is used in the spam package.

cov.fixed_nugget_value (default: NA)

A constant value for the nugget parameter. Note that the code assumes that the last value of theta corresponds to the nugget parameter, as this notation is used in the spam package.

Note that if either of these arguments are specified, the corresponding entries should also be omitted in theta.

Value

A function of the form function(h, theta). This function is enclosed in the execution environment of choleskyFactory and hence has access to the arguments covariance and cov.args. The manufactured function returns the result of covariance(h = h, theta = theta, cov.args = cov.args).

Author(s)

Thomas Caspar Fischer

References

Wickham, H. (2015) Advanced R, CRC Press.

See Also

covmat and cov.wendland

Examples

library(GeneralizedWendland)
library(spam)

hs <- seq(0, 1, 0.05)
covSph <- covarianceFactory(cov.sph)
covExp <- covarianceFactory(cov.exp)
covWend <- covarianceFactory(cov.wendland)

plot(0, type = "n", xlim = c(0, 1), ylim = c(0, 1))
lines(hs, covSph(hs, theta = c(0.5, 1, 0)))
lines(hs, covExp(hs, theta = c(0.5, 1, 0)), col = "red")
lines(hs, covWend(hs, theta = c(0.5, 1, 0.5, 0.5, 0)), col = "green")