Package 'simpleMH'

Title: Simple Metropolis-Hastings MCMC Algorithm
Description: A very bare-bones interface to use the Metropolis-Hastings Monte Carlo Markov Chain algorithm. It is suitable for teaching and testing purposes.
Authors: Hugo Gruson [aut, cre, cph]
Maintainer: Hugo Gruson <[email protected]>
License: GPL-3
Version: 0.1.1.9000
Built: 2024-10-06 04:03:32 UTC
Source: https://github.com/bisaloo/simpleMH

Help Index


Simple Metropolis-Hastings MCMC

Description

Simple Metropolis-Hastings MCMC

Usage

simpleMH(f, inits, theta.cov, max.iter, coda = FALSE, ...)

Arguments

f

function that returns a single scalar value proportional to the log probability density to sample from.

inits

numeric vector with the initial values for the parameters to estimate

theta.cov

covariance matrix of the parameters to estimate.

max.iter

maximum number of function evaluations

coda

logical. Should the samples be returned as coda::mcmc object? (defaults to FALSE)

...

further arguments passed to f

Value

  • if coda = FALSE a list with:

    • samples: A two dimensional array of samples with dimensions generation x parameter

    • log.p: A numeric vector with the log density evaluate at each generation.

  • if coda = TRUE a list with:

    • samples: A object of class coda::mcmc containing all samples.

    • log.p: A numeric vector with the log density evaluate at each generation.

Examples

p.log <- function(x) {
B <- 0.03
return(-x[1]^2/200 - 1/2*(x[2]+B*x[1]^2-100*B)^2)
}

simpleMH(p.log, inits=c(0, 0), theta.cov = diag(2), max.iter=3000)