ooDACE toolbox  1.4
 All Classes Files Functions Variables Pages
Functions
oodacefit.m File Reference

Functions

function oodacefit (var samples, var values, var userOpts)
 Creates and fits a kriging model with sensible options.
 

Detailed Description

Authors
Ivo Couckuyt
Version
1.4 ($Revision$)
Date
$LastChangedDate$
Copyright 2010-2013

This file is part of the ooDACE toolbox and you can redistribute it and/or modify it under the terms of the GNU Affero General Public License version 3 as published by the Free Software Foundation. With the additional provision that a commercial license must be purchased if the ooDACE toolbox is used, modified, or extended in a commercial setting. For details see the included LICENSE.txt file. When referring to the ooDACE toolbox please make reference to the corresponding publications:

Contact : ivo.c.nosp@m.ouck.nosp@m.uyt@u.nosp@m.gent.nosp@m..be - http://sumo.intec.ugent.be/?q=ooDACE Signature k = oodacefit( samples, values, userOpts )

Function Documentation

function oodacefit ( var  samples,
var  values,
var  userOpts 
)

Creates and fits a kriging model with sensible options.

        For easy fitting when you don't care much about parameters.
        The function tries to determine the best kriging model to use:
        - samples is numeric array -> kriging
        - samples is cell array -> cokriging
Parameters
samplesinput sample matrix
valuesoutput value matrix
userOptsstruct of user options (optional)
  • userOpts.type overrides the type of kriging model to use, e.g., "BasicGaussianProcess", "Kriging", "CoKriging", etc.
  • For regression kriging set the following fields:
    • userOpts.lambda0 = 0;
    • userOpts.lambdaBounds = [-5 ; 5]; % log scale
  • For stochastic kriging set the following fields:
    • userOpts.Sigma = SigmaVector; % variance of the output values
    • userOpts.sigma20 = 1;
    • userOpts.sigma2Bounds = [0.001 ; 150];
  • Please see the BasicGaussianProcess::getDefaultOptions(), Kriging::getDefaultOptions(), etc. methods for more options.
Return values
ka ready-to-use kriging model