label.switching: An R Package for Dealing with the Label Switching Problem in MCMC Outputs

TL;DR

This paper introduces the R package 'label.switching' which provides multiple algorithms to address the label switching problem in MCMC outputs for Bayesian mixture and hidden Markov models, improving post-processing of samples.

Contribution

The paper presents a comprehensive R package with one probabilistic and seven deterministic relabelling algorithms for post-processing MCMC samples, facilitating better inference in mixture models.

Findings

Provides a set of relabelling algorithms for MCMC post-processing

Enables benchmarking of new relabelling methods

Improves the interpretability of Bayesian mixture model outputs

Abstract

Label switching is a well-known and fundamental problem in Bayesian estimation of mixture or hidden Markov models. In case that the prior distribution of the model parameters is the same for all states, then both the likelihood and posterior distribution are invariant to permutations of the parameters. This property makes Markov chain Monte Carlo (MCMC) samples simulated from the posterior distribution non-identifiable. In this paper, the \pkg{label.switching} package is introduced. It contains one probabilistic and seven deterministic relabelling algorithms in order to post-process a given MCMC sample, provided by the user. Each method returns a set of permutations that can be used to reorder the MCMC output. Then, any parametric function of interest can be inferred using the reordered MCMC sample. A set of user-defined permutations is also accepted, allowing the researcher to benchmark new relabelling methods against the available ones