daceObjfunc: DACE objective function

In SPOT: Sequential Parameter Optimization Toolbox

DACE objective function

Description

Evaluate the fit of a certain set of model parameters (theta), and get all relevant variables of the model.

Usage

daceObjfunc(theta, pars, what = "all")

Arguments

theta	model parameters to be evaluated
pars	model option list, as created with dacePrepareFit
what	a string: "all" both the likelihood (f) and the model list (fit) will be returned, "f" and "fit specify to return only those.

Value

A list of two elements (which are NA if what is specified accordingly)
f likelihood
fit also a list list of model variables, with the following elements:

beta	generalized least squares estimate
gamma	correlation factors
sigma2	maximum Likelihood estimate of the process variance
C	Cholesky factor of correlation matrix
Ft	Decorrelated regression matrix
G	From QR factorization: Ft = Q*t(G)

Author(s)

The authors of the original DACE Matlab code are Hans Bruun Nielsen, Soren Nymand Lophaven and Jacob Sondergaard.
Extension of the Matlab code by Tobias Wagner [e-mail].
Porting and adaptation to R and further extensions by Martin Zaefferer [e-mail].

See Also

buildKrigingDACE daceLikelihood daceEvalFit

SPOT documentation built on June 26, 2022, 1:06 a.m.