buildKrigingDACE: Build DACE model

Description

This Kriging meta model is based on DACE (Design and Analysis of Computer Experiments). It allows to choose different regression and correlation models. The optimization of model parameters is by default done with a bounded simplex method from the nloptr package.

Usage

buildKrigingDACE(x, y, control = list())

Arguments

design matrix (sample locations), rows for each sample, columns for each variable.

vector of observations at x

control

(list), with the options for the model building procedure: startTheta optional start value for theta optimization, default is NULL algTheta algorithm used to find theta, default is optimDE. budgetAlgTheta budget for the above mentioned algorithm, default is 200. The value will be multiplied with the length of the model parameter vector to be optimized. nugget Value for nugget. Default is -1, which means the nugget will be optimized during MLE. Else it can be fixed in a range between 0 and 1. regr Regression function to be used: regpoly0 (default), regpoly1, regpoly2. Can be a custom user function. corr Correlation function to be used: corrnoisykriging (default), corrkriging, corrnoisygauss, corrgauss, correxp, correxpg, corrlin, corrcubic,corrspherical,corrspline. Can also be user supplied (if in the right form). target target values of the prediction, a vector of strings. Each string specifies a value to be predicted, e.g., "y" for mean, "s" for standard deviation, "ei" for expected improvement. See also predict.kriging. This can also be changed after the model has been build, by manipulating the respective object$target value.

Value

returns an object of class dace with the following elements:

model

A list, containing model parameters

like

Estimated likelihood value

theta

activity parameters theta (vector)

p

exponents p (vector)

lambda

nugget value (numeric)

nevals

Number of iterations during MLE

References

S.~Lophaven, H.~Nielsen, and J.~Sondergaard. DACE---A Matlab Kriging Toolbox. Technical Report IMM-REP-2002-12, Informatics and Mathematical Modelling, Technical University of Denmark, Copenhagen, Denmark, 2002.

Examples

Run this code

# NOT RUN {
## Create design points
x <- cbind(runif(20)*15-5,runif(20)*15)
## Compute observations at design points 
y <- funSphere(x)
## Create model with default settings
fit <- buildKrigingDACE(x,y)
## Print model parameters
print(fit)
## Create with different regression and correlation functions
fit <- buildKrigingDACE(x,y,control=list(regr=regpoly2,corr=corrspline))
## Print model parameters
print(fit)

# }