| Wendland {fields} | R Documentation |
Computes the compactly supported, stationatry Wendland covariance function as a function ofdistance. This family is useful for creating sparse covariance matrices.
Wendland(d, theta = 1, dimension, k,derivative=0, phi=1) Wendland2.2(d, theta=1) wendland.coef(d,k)
d |
Distances between locations. Or for wendland.coef the dimension of the locations. |
theta |
Scale for distances. This is the same as the range parameter. |
dimension |
Dimension of the locations |
k |
Order of covariance function. |
derivative |
Indicates derivative of covariance function |
phi |
Scale factor to multiply the function. Equivalent to the marginal variance or sill if viewed as a covariance function. |
This is the basic function applied to distances and called by the
wendland.cov function. It can also be used as the Covariance or
Taper specifications in the more general
stationary.cov and station.taper.cov functions.
The Wendland covariance function is a
polynomial on [0,theta] and zero beyond theta.
The parameter k detemines the smoothness of the covariance at zero.
The polynomial
coefficients are computed recursively based on the values of k
and dimension in the function wendland.coef. The
polynomial is evaluated using fields.evlpoly.
A specific example of the Wendland family is Wendland2.2 and this
is included mainly for testing.
A vector of the covariances or its derivative.
Doug Nychka
wendland.cov, stationary.taper.cov
DD<- seq( 0,1.5,, 200) y<- Wendland( DD, k=2, dimension=2) plot( DD, y, type="l") # should agree with y.test<- Wendland2.2( DD)