predict.se.krig {funfits} | R Documentation |
The predictions are represented as a linear combination of the dependent variable, Y. Based on this representation the conditional variance is the same as the expected value of (P(x) + Z(X) - LY)^2. where P(x)+Z(x) is the value of the surface at x and LY is the linear combination that estimates this point. Finding this expected value is straight forward given the unbiasedness of LY for P(x) and the covariance for Z and Y. In these calculations is assumed that the covariance parameters are fixed. This is an approximation since in most cases they have been estimated from the data. Note that the linear commbination is based on the covariance function from the krig object. The covariance for the random surface may be this same fucntion or another if it is explicitly passed as an argument. See the FUNFITS manual for more details.
predict.se.krig(out, x, se=F, cov.fun, rho, sigma2, stationary=T)
out |
A fitted krig object. |
x |
Matrix of x values on which to calculate the standard errors of predictions of the thin plate spline regression. If omitted, the out$x will be used. |
se |
~Describe se here |
cov.fun |
Covariance function for the random surface. If omitted then the function from the krig object ( out$cov.function) is used. |
rho |
Parameter that multiplies cov.function. If omitted the value out$rho, estimated from the data is used. |
sigma2 |
Variance of the measurement error. If omitted the value out$sigma2, estimated from the data is used |
stationary |
If true the covariance function is assumed to be stationary and more efficient computations can be made. |
A vector of standard errors for the predicted values of the kriging fit.
krig, predict.krig
krig(ozone$x,ozone$y,exp.cov) -> fit # krig fit predict.se.krig(fit) # std errors of predictions cbind(seq(87,89,,10),seq(40,42,,10)) -> x # new x matrix predict.se.krig(fit,x) -> out # std errors of predictions