cmce (version 0.1.0)

Computer Model Calibration for Deterministic and Stochastic Simulators

Description

Implements the Bayesian calibration model described in Pratola and Chkrebtii (2018) for stochastic and deterministic simulators. Additive and multiplicative discrepancy models are currently supported. See for more information and examples.

Copy Link

Version

Install

install.packages('cmce')

Monthly Downloads

188

Version

0.1.0

License

AGPL-3

Maintainer

Matthew Pratola

Last Published

May 24th, 2018

Functions in cmce (0.1.0)

scaledesign

Rescale a design matrix to the [0,1] hypercube.

gp.realize

Draw an unconditional GP realization.

calibrate

Fit the calibration model.

getranges

Get variable ranges from a design matrix.

unscalemat

Unscale a matrix back to its original ranges.

makedistlist

Make list of distance matrices for calculating GP correlation matrices.

cmce-package

cmce is an open-source R package implementing Bayesian calibration for deterministic and stochastic simulation models.