Learn R Programming

CaliCo (version 0.1.1)

Code Calibration in a Bayesian Framework

Description

Calibration of every computational code. It uses a Bayesian framework to rule the estimation. With a new data set, the prediction will create a prevision set taking into account the new calibrated parameters. The choices between several models is also available. The methods are described in the paper Carmassi et al. (2018) .

Copy Link

Version

Install

install.packages('CaliCo')

Monthly Downloads

11

Version

0.1.1

License

GPL (>= 2)

Maintainer

Mathieu Carmassi

Last Published

July 24th, 2018

Functions in CaliCo (0.1.1)

model.class

A Reference Class to generates differents model objects
estimators

Return Maximum A Posteriori (MAP) and Mean A Posteriori estimation of a calibration
Kernel.class

A Reference Class to generates differents model objects
MetropolisHastingsCpp

C++ implementation of the algorithm for parameter calibration (without discrepancy)
prior

Generates prior.class objects.
multivariate

Simulate from a Multivariate Normal Distribution
CaliCo

Bayesian calibration for computational codes
prior.class

A Reference Class to generate differents prior.class objects
forecast

Generates a forecast base on calibration run with calibrate
unscale

Function which unscale un matrix or a vector
MetropolisHastingsCppD

C++ implementation of the algorithm for parameter calibration (with discrepancy)
DefPos

Function that deals with negative eigen values in a matrix not positive definite
unscale.matrix.diag

Function which unscale only the diagonal component of a matrix
calibrate

Generates calibrate.class objects
calibrate.class

A Reference Class to generates different calibrate.class objects
kernel.fun

Generates covariances matrices thanks to Kernel.class
model

Generates model.class objects.
forecast.class

A Reference Class to generates differents forecast.class objects
%<%

Operator to define active bindings variables
chain

Return the MCMC chain in a data.frame
seqDesign.class

A Reference Class to generate a better Model2 or Model4 model.class objects
sequentialDesign

Calibration with a sequential design
unscale.vector

Function which unscale a vector between two bounds