Learn R Programming

⚠️There's a newer version (0.1.8) of this package.Take me there.

BayesianTools (version 0.1.0)

General-Purpose MCMC and SMC Samplers and Tools for Bayesian Statistics

Description

General-purpose MCMC and SMC samplers, as well as plot and diagnostic functions for Bayesian statistics, with a particular focus on calibrating complex system models. Implemented samplers include various Metropolis MCMC variants (including adaptive and/or delayed rejection MH), the T-walk, two differential evolution MCMCs, two DREAM MCMCs, and a sequential Monte Carlo (SMC) particle filter.

Copy Link

Version

Install

install.packages('BayesianTools')

Monthly Downloads

898

Version

0.1.0

License

CC BY-SA 4.0

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/florianhartig/BayesianTools

Maintainer

Florian Hartig

Last Published

February 6th, 2017

Functions in BayesianTools (0.1.0)

The Adaptive Metropolis Algorithm

Creates a standardized prior class

createSmcSamplerList

Convenience function to create an object of class SMCSamplerList from a list of mcmc samplers

createBetaPrior

Convenience function to create a beta prior

createMcmcSamplerList

Convenience function to create an object of class mcmcSamplerList from a list of mcmc samplers

createProposalGenerator

Factory that creates a proposal generator

createPriorDensity

Fits a density function to a multivariate sample

createPosterior

Creates a standardized posterior class

createTruncatedNormalPrior

Convenience function to create a truncated normal prior

createLikelihood

Creates a standardized likelihood class

createMixWithDefaults

Allows to mix a given parameter vector with a default parameter vector

The Delayed Rejection Algorithm

gelmanDiagnostics

Runs Gelman Diagnotics over an Bayesianutput

The Delayed Rejection Adaptive Metropolis Algorithm

createUniformPrior

Convenience function to create a simple uniform prior distribution

Differential-Evolution MCMC

Deviance information criterion

Differential-Evolution MCMC zs

getPredictiveIntervals

Calculates Bayesian credible (confidence) and predictive intervals based on parameter sample

getPredictiveDistribution

Calculates predictive distribution based on the parameters

generateParallelExecuter

Factory to generate a parallel executer of an existing function

generateCRvalues

Generates matrix of CR values based on pCR

calculates the Maxiumum APosteriori value (MAP)

marginalLikelihood

Calcluated the marginal likelihood from a set of MCMC samples

getBlockSettings

getblockSettings

getCredibleIntervals

Calculate confidence region from an MCMC or similar sample

getPossibleSamplerTypes

Returns possible sampler types

Calculates the panel combination for par(mfrow = )

Funktion to compute log(sum(exp(x))

likelihoodIidNormal

Normal / Gaussian Likelihood function

Helper function for sum of x*x

plotTimeSeriesResiduals

Plots residuals of a time series

plotTimeSeriesResults

Creates a time series plot typical for an MCMC / SMC fit

mcmcMultipleChains

Run multiple chains

generateTestDensityMultiNormal

Multivariate normal likelihood

Determine the parameters in the block update

Plot MCMC marginals

Function to close cluster in BayesianSetup

Main function that is executing and evaluating the moves

The Metropolis Algorithm

Determine the groups of correlated parameters

setupStartProposal

Help function to find starvalues and proposalGenerator settings

updateProposalGenerator

To update settings of an existing proposal genenerator

Wrapper for step function

Helper function to create proposal

Main wrapper function to start MCMCs, particle MCMCs and SMCs

makeObjectClassCodaMCMC

Helper function to change an object to a coda mcmc class,

Extracts the sample from a bayesianOutput

testDensityInfinity

Test function infinity ragged

Create a random radiation (PAR) time series

VSEMgetDefaults

returns the default values for the VSEM

Produce multivariate normal proposal

testLinearModel

Fake model, returns a ax + b linear response to 2-param vector

plotSensitivity

Performs a one-factor-at-a-time sensitivity analysis for the posterior of a given bayesianSetup within the prior range.

Plots a time series, with the option to include confidence and prediction band

Function to thin matrices

testDensityBanana

Banana-shaped density function

C version of the VSEM model

VSEMcreateLikelihood

Create an example dataset, and from that a likelihood or posterior for the VSEM model

Helper function for blow and hop moves

testDensityNormal

Normal likelihood

sampleMetropolis

gets samples while adopting the MCMC proposal generator

Creates a Metropolis-type MCMC with options for covariance adaptatin, delayed rejection, Metropolis-within-Gibbs, and tempering

metropolisRatio

Funktion to calculate the metropolis ratio

testDensityMultiNormal

3d Mutivariate Normal likelihood

AR1 type likelihood function

Function to scale matrices

Trace plot for MCMC class

Function to combine chains

Convert coda::mcmc objects to BayesianTools::mcmcSampler

checkBayesianSetup

Checks if an object is of class 'BayesianSetup'

applySettingsDefault

Provides the default settings for the different samplers in runMCMC

Helper function for calculating beta

Adapts pCR values

correlationPlot

Flexible function to create correlation density plots

createBayesianSetup

Creates a standardized collection of prior, likelihood and posterior functions, including error checks etc.

Very simple ecosystem model

calculates the WAIC