createTrimodalTarget: Trimodal target distribution
In PAWL: Implementation of the PAWL algorithm

Description Usage Details Value Author(s) References See Also

Create the trimodal distribution as in Liang, Liu and Caroll, 2007: Stochastic approximation in Monte Carlo computation.

1	createTrimodalTarget()

This distribution is a mixture of three bivariate Gaussian distributions. Their covariance matrices are such that an adaptive MCMC algorithm which proposal variance adapts to one of the component, will likely fail to explore the others.

The function returns an object of class target, with a name, a dimension, a function giving the log density, a function to generate sample from the distribution, parameters of the distribution, and a function to draw init points for the MCMC algorithms.

Luke Bornn <bornn@stat.harvard.edu>, Pierre E. Jacob <pierre.jacob.work@gmail.com>

Liang, Liu and Caroll: Stochastic approximation in Monte Carlo computation. Published in JASA, 2007.

target, createMixtureTarget

PAWL documentation built on May 2, 2019, 5:58 a.m.