⚠️There's a newer version (1.2-8) of this package.Take me there.

approximator (version 1.2-7)

Bayesian Prediction of Complex Computer Codes

Description

Performs Bayesian prediction of complex computer codes when fast approximations are available. It uses a hierarchical version of the Gaussian process, originally proposed by Kennedy and O'Hagan (2000), Biometrika 87(1):1.

Copy Link

Version

Install

install.packages('approximator')

Monthly Downloads

310

Version

1.2-7

License

GPL-2

Maintainer

Robin K S Hankin

Last Published

August 29th, 2018

Functions in approximator (1.2-7)

is.consistent

Checks observational data for consistency with a subsets object

toyapps

Toy datasets for approximator package

tee.fun

Returns generalized distances

generate.toy.observations

Er, generate toy observations

c.fun

Correlations between points in parameter space

basis.toy

Toy basis functions

mdash.fun

Mean of Gaussian process

object

Optimization of posterior likelihood of hyperparameters

betahat.app

Estimate for beta

subset_maker

Create a simple subset object

subsets.fun

Generate and test subsets

approximator-package

Bayesian approximation of computer models when fast approximations are available

as.sublist

Converts a level one design matrix and a subsets object into a list of design matrices, one for each level

genie

Genie datasets for approximator package

Kennedy's Pi notation

V.fun.app

Variance matrix

Afun

Matrix of correlations between two sets of points

H.fun

The H matrix

hpa.fun.toy

Toy example of a hyperparameter object creation function

hdash.fun

Hdash