modelPredict function

Prediction at newdata for a fitted metamodel

modelPredict computes predicted values based on the model given in argument.

modelPredict(model,newdata)

Arguments

• model: a fitted model obtained from modelFit
• newdata: a matrix (or a data frame) which represents the predictor values at which the fitted values will be computed.

Returns

a vector of predicted values, obtained by evaluating the model at newdata.

Author(s)

D. Dupuy

See Also

modelFit

Examples

X  <- seq(-1,1,l=21)
Y  <- 3*X + rnorm(21,0,0.5)
# construction of a linear model
modLm <- modelFit(X,Y,type = "Linear",formula="Y~.")
print(modLm$model$coefficient)

## Not run:

# illustration on a 2-dimensional example
Branin  <- function(x1,x2) {
x1      <- 1/2*(15*x1+5)   
x2      <- 15/2*(x2+1)
(x2 - 5.1/(4*pi^2)*(x1^2) + 5/pi*x1 - 6)^2 + 10*(1 - 1/(8*pi))*cos(x1) + 10
}
# A 2D uniform design with 20 points in [-1,1]^2
n       <- 20
X       <- matrix(runif(n*2,-1,1),ncol=2,nrow=n)
Y       <- Branin(X[,1],X[,2])
Z       <- (Y-mean(Y))/sd(Y)

# Construction of a Kriging model
mKm     <- modelFit(X,Z,type = "Kriging")

# Prediction and comparison between the exact function and the predicted one
xtest   <- seq(-1, 1, length= 21) 
ytest   <- seq(-1, 1, length= 21)
Zreal   <- outer(xtest, ytest, Branin)
Zreal   <- (Zreal-mean(Y))/sd(Y)
Zpredict        <- modelPredict(mKm,expand.grid(xtest,ytest))

z <- abs(Zreal-matrix(Zpredict,nrow=length(xtest),ncol=length(ytest)))
contour(xtest, xtest, z,30)
points(X,pch=19)
## End(Not run)