KM-class

This class is intended to be used either by using its
 own dedicated S4 methods or by using the S4 methods inherited
 from the <code>"km"</code> class of the libKriging package.

Interface to 'libKriging' 'C++' library <https://github.com/libKriging> that should
provide most standard Kriging / Gaussian process regression features
(like in 'DiceKriging', 'kergp' or 'RobustGaSP' packages).
'libKriging' relies on Armadillo linear algebra library (Apache 2 license) by Conrad Sanderson,
'lbfgsb_cpp' is a 'C++' port around by Pascal Have of 'lbfgsb' library (BSD-3 license) by
Ciyou Zhu, Richard Byrd, Jorge Nocedal and Jose Luis Morales used for hyperparameters optimization.

Yann Richet

rlibkriging

Kriging Models using the 'libKriging' Library

Pascal Havé

Yves Deville

Conrad Sanderson

Ciyou Zhu

Richard Byrd

Jorge Nocedal

Jose Luis Morales

Mike Smith

KM-class function

<dl>
<dt><code>d,n,X,y,p,F</code></dt>
<dd>Number of (numeric) inputs, number of
observations, design matrix, response vector, number of trend
variables, trend matrix.</dd></dl>
<dt><code>trend.formula,trend.coef</code></dt>
<dd>Formula used for the trend, vector
\(\hat{\boldsymbol{\beta}}\) of estimated (or fixed)
trend coefficients with length \(p\).</dd>
<dt><code>covariance</code></dt>
<dd>A S4 object with class <code>"covTensorProduct"</code>
representing a covariance kernel.</dd>
<dt><code>noise.flag,noise.var</code></dt>
<dd>Logical flag and numeric value for an
optional noise term.</dd>
<dt><code>known.param</code></dt>
<dd>A character code indicating what parameters are
known.</dd>
<dt><code>lower,upper</code></dt>
<dd>Bounds on the correlation range parameters.</dd>
<dt><code>method,penalty,optim.method,control,gr,parinit</code></dt>
<dd>Objects
defining the estimation criterion, the optimization.</dd>
<dt><code>T,M,z</code></dt>
<dd>Auxiliary variables (matrices and vectors) that can be
used in several computations.</dd>
<dt><code>case</code></dt>
<dd>The possible concentration (a.k.a. profiling) of the
likelihood.</dd>
<dt><code>param.estim</code></dt>
<dd>Logical. Is an estimation used?</dd>
<dt><code>Kriging</code></dt>
<dd>A copy of the <code>Kriging</code> object used to create
the current <code>KM</code> object.</dd>

Slots

Yann Richet <a href="/link/yann.richet%40asnr.fr?package=rlibkriging&version=0.9-2.3" data-mini-rdoc="rlibkriging::yann.richet@asnr.fr">yann.richet@asnr.fr</a>

Author

S4 class for Kriging Models Extending the "km" Class — KM-class

<dl>
<dt><code>d,n,X,y,p,F</code></dt>
<dd>Number of (numeric) inputs, number of
observations, design matrix, response vector, number of trend
variables, trend matrix.</dd>


<dt><code>trend.formula,trend.coef</code></dt>
<dd>Formula used for the trend, vector
\(\hat{\boldsymbol{\beta}}\) of estimated (or fixed)
trend coefficients with length \(p\).</dd>


<dt><code>covariance</code></dt>
<dd>A S4 object with class <code>"covTensorProduct"</code>
representing a covariance kernel.</dd>


<dt><code>noise.flag,noise.var</code></dt>
<dd>Logical flag and numeric value for an
optional noise term.</dd>


<dt><code>known.param</code></dt>
<dd>A character code indicating what parameters are
known.</dd>


<dt><code>lower,upper</code></dt>
<dd>Bounds on the correlation range parameters.</dd>


<dt><code>method,penalty,optim.method,control,gr,parinit</code></dt>
<dd>Objects
defining the estimation criterion, the optimization.</dd>


<dt><code>T,M,z</code></dt>
<dd>Auxiliary variables (matrices and vectors) that can be
used in several computations.</dd>


<dt><code>case</code></dt>
<dd>The possible concentration (a.k.a. profiling) of the
likelihood.</dd>


<dt><code>param.estim</code></dt>
<dd>Logical. Is an estimation used?</dd>


<dt><code>Kriging</code></dt>
<dd>A copy of the <code>Kriging</code> object used to create
the current <code>KM</code> object.</dd>


</dl>

Yann Richet <a href='mailto:yann.richet@asnr.fr'>yann.richet@asnr.fr</a>

KM-class: S4 class for Kriging Models Extending the `"km"` Class

Description

Arguments

Slots

Author

See Also