predict.Krig: Evaluation of Krig spatial process estimate.

Description

Provides predictions from the Krig spatial process estimate at arbitrary points, new data (Y) or other values of the smoothing parameter (lambda) including a GCV estimate.

Usage

predict.Krig
(out, x = NULL, lambda = NA, df = NA, model = NA,
        eval.correlation.model = TRUE, y = NULL, verbose = FALSE, gcv = FALSE)

Arguments

Value

Vector of predicted responses if gcv=F ( the default) BUT NOTE: If lambda is found by gcv then the returned values is a list with the first component a vector of predictions and the second the estimated value of lambda.

Details

The main goal in this function is to reuse the Krig object to rapidly evaluate different estimates. Thus there is flexibility in changing the value of lambda and also the independent data without having to recompute the matrices associated with the Krig object. The reason this is possible is that most on the calculations depend on the observed locations not on lambda or the observed data.

Examples

Run this code

Krig(ozone$x,ozone$y,exp.cov, theta=50) ->fit
predict( fit) # gives predicted values at data points

grid<- make.surface.grid( list( seq( -40,40,,15), seq( -40,40,,15)))

look<- predict(fit,grid) # evaluate on a grid of points

# some useful graphing functions
out.p<- as.surface( grid, look) # reformat into $x $y $z image-type object
contour( out.p)  


# refit with 10 degrees of freedom in surface

look<- predict(fit,grid, df=15)

# re fit with random data and lambda found by GCV
look<- predict( fit, grid, y= rnorm( 20), gcv=TRUE)

# NOTE: look is a list now  look$predicted  predicted values and look$lambda
# the value of lambda

out.p<-as.surface( grid, look$predicted) 
contour( out.p)