Efficient Bayesian inference for stochastic volatility models with ensemble MCMC methods

TL;DR

This paper presents ensemble MCMC methods that significantly improve Bayesian inference efficiency for univariate stochastic volatility models, outperforming existing samplers by a factor of over three without assuming linear Gaussian latent processes.

Contribution

Introduction of ensemble MCMC sampling methods that enhance Bayesian inference efficiency for stochastic volatility models without restrictive assumptions.

Findings

Ensemble MCMC is 3.1 times more efficient than previous methods.

The new sampler does not require the latent process to be linear and Gaussian.

Performance gains are demonstrated on simulated data.

Abstract

In this paper, we introduce efficient ensemble Markov Chain Monte Carlo (MCMC) sampling methods for Bayesian computations in the univariate stochastic volatility model. We compare the performance of our ensemble MCMC methods with an improved version of a recent sampler of Kastner and Fruwirth-Schnatter (2014). We show that ensemble samplers are more efficient than this state of the art sampler by a factor of about 3.1, on a data set simulated from the stochastic volatility model. This performance gain is achieved without the ensemble MCMC sampler relying on the assumption that the latent process is linear and Gaussian, unlike the sampler of Kastner and Fruwirth-Schnatter.