R: PP GaSP class

ppgasp-class {RobustGaSP}

R Documentation

PP GaSP class

Description

S4 class for PP GaSP model if the range and noise-variance ratio parameters are given and/or have been estimated.

Objects from the Class

Objects of this class are created and initialized with the function ppgasp that computes the calculations needed for setting up the analysis.

Slots

p:

Object of class integer. The dimensions of the inputs.

num_obs:

Object of class integer. The number of observations.

k:

Object of class integer. The number of outputs in each computer model run.

input:

Object of class matrix with dimension n x p. The design of experiments.

output:

Object of class matrix with dimension n x k. Each row denotes a output vector in each run of the computer model.

X:

Object of class matrix of with dimension n x q. The mean basis function, i.e. the trend function.

zero_mean:

A character to specify whether the mean is zero or not. "Yes" means it has zero mean and "No"" means the mean is not zero.

q:

Object of class integer. The number of mean basis.

LB:

Object of class vector with dimension p x 1. The lower bound for inverse range parameters beta.

beta_initial:

Object of class vector with the initial values of inverse range parameters p x 1.

beta_hat:

Object of class vector with dimension p x 1. The inverse-range parameters.

log_post:

Object of class numeric with the logarithm of marginal posterior.

R0:

Object of class list of matrices where the j-th matrix is an absolute difference matrix of the j-th input vector.

theta_hat:

Object of class vector with dimension q x 1. The the mean (trend) parameter.

L:

Object of class matrix with dimension n x n. The Cholesky decomposition of the correlation matrix R, i.e.

L\%*\%t(L)=R

sigma2_hat:

Object of the class matrix. The estimated variance parameter of each output.

LX:

Object of the class matrix with dimension q x q. The Cholesky decomposition of the correlation matrix

t(X)\%*\%R^{-1}\%*\%X

CL:

Object of the class vector used for the lower bound and the prior.

nugget:

A numeric object used for the noise-variance ratio parameter.

nugget.est:

A logical object of whether the nugget is estimated (T) or fixed (F).

kernel_type:

A vector of character to specify the type of kernel to use.

alpha:

Object of class vector with dimension p x 1 for the roughness parameters in the kernel.

method:

Object of class character to specify the method of parameter estimation. There are three values: post_mode, mle and mmle.

isotropic:

Object of class logical to specify whether the kernel is isotropic.

call:

The call to ppgasp function to create the object.

Methods

show: Prints the main slots of the object.
predict: See predict.

Author(s)

Mengyang Gu [aut, cre], Jesus Palomo [aut], James Berger [aut]