predict.QKResults: Revaluate Quantiles

In quantkriging: Quantile Kriging for Stochastic Simulations with Replication

Description

Quantile Predictions using Quantile Kriging model (class QKResults)

Usage

## S3 method for class 'QKResults'
predict(object, xnew, quantnew = NULL, ...)

Arguments

object	Output from the quantKrig function.
xnew	Locations for prediction
quantnew	Quantiles for prediction, default is to keep the same as the quantile object
...	Ignore. No other arguments for this method

Value

Quantile predictions at the specified input locations

Author(s)

Kevin Quinlan [e-mail]

Examples

X <- seq(0,1,length.out = 20)
Y <- cos(5*X) + cos(X)
Xstar <- rep(X,each = 100)
Ystar <- rep(Y,each = 100)
e <- rchisq(length(Ystar),5)/5 - 1
Ystar <- Ystar + e
lb <- c(0.0001,0.0001)
ub <- c(10,10)
Qout <- quantKrig(Xstar,Ystar, seq(0.05,0.95, length.out = 7), lower = lb, upper = ub)

predict(Qout, xnew = c(0.4, 0.5, 0.6))

quantpreds <- predict(Qout, xnew = seq(0,1,length.out = 100), quantnew = seq(0.01,0.99,by = 0.01))
matplot(seq(0,1,length.out = 100), quantpreds, type = 'l')

quantkriging documentation built on March 13, 2020, 2:54 a.m.