R_stat: Gelman-Rubin convergence diagnostic

Description Usage Arguments Details Value Author(s) References

View source: R/gelman_rubin.R

Description

Calculates diagnostic values to determine convergence of a MCMC algorithm.

Usage

1
R_stat(x)

Arguments

x

numeric array of [no. of samples]-by-[no. of parameters]-by-[no. of chains] dimensions

Details

The Gelman-Rubin value should be <= 1.2 for all parameters to declare convergence. Otherwise the number of samples should be increased.

Value

A [no. of parameters]-dimensional vector of Gelman-Rubin diagnostic values.

Author(s)

Tobias Pilz tpilz@uni-potsdam.de

References

Algorithm based on Gelman and Rubin (1992) obtained from (Eqs. 32-35):

Vrugt, J. A.: "Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation." Environmental Modelling & Software, 2016, 75, 273 – 316, http://dx.doi.org/10.1016/j.envsoft.2015.08.013.


tpilz/HydroBayes documentation built on May 6, 2019, 3:44 p.m.