Learn R Programming

MCMChybridGP (version 5.4)

Hybrid Markov Chain Monte Carlo using Gaussian Processes

Description

Hybrid Markov chain Monte Carlo (MCMC) to simulate from a multimodal target distribution. A Gaussian process approximation makes this possible when derivatives are unknown. The Package serves to minimize the number of function evaluations in Bayesian calibration of computer models using parallel tempering. It allows replacement of the true target distribution in high temperature chains, or complete replacement of the target. Methods used are described in, "Efficient MCMC schemes for computationally expensive posterior distributions", Fielding et al. (2011) . The research presented in this work was carried out as part of the Singapore-Delft Water Alliance Multi-Objective Multi-Reservoir Management research programme (R-264-001-272).

Copy Link

Version

Install

install.packages('MCMChybridGP')

Monthly Downloads

54

Version

5.4

License

GPL-2

Maintainer

Mark Fielding

Last Published

November 12th, 2020

Functions in MCMChybridGP (5.4)

MCMChybridGP-package

Hybrid MCMC for a multimodal density with derivatives replaced by Gaussian process
hybrid.sample

Sampling phase applying results from Exploratory phase.
generateX0

Generate some initial points for the hybrid explore phase
GProcess

Determine a Gaussian process fit to a multivariate log-density function.
hybrid.explore

Exploratory phase to determine points used for a Gaussian process fit.
MCMChybridGP-internal

Internal MCMChybridGP objects