On Disturbance State-Space Models and the Particle Marginal Metropolis-Hastings Sampler

TL;DR

This paper introduces a reformulation of nonlinear state-space models over latent noise variables to enable importance sampling, and demonstrates its effectiveness in marine biogeochemical models using particle marginal Metropolis-Hastings.

Contribution

It proposes a novel reformulation of models over noise variables and compares proposal strategies, improving inference in models with intractable transition densities.

Findings

Reformulation over noise variables enhances importance sampling.

Proposal strategies based on lookaheads improve Metropolis-Hastings efficiency.

Reformulation is especially useful for fast-mixing process models.

Abstract

We investigate nonlinear state-space models without a closed-form transition density, and propose reformulating such models over their latent noise variables rather than their latent state variables. In doing so the tractable noise density emerges in place of the intractable transition density. For importance sampling methods such as the auxiliary particle filter, this enables importance weights to be computed where they could not be otherwise. As case studies we take two multivariate marine biogeochemical models and perform state and parameter estimation using the particle marginal Metropolis-Hastings sampler. For the particle filter within this sampler, we compare several proposal strategies over noise variables, all based on lookaheads with the unscented Kalman filter. These strategies are compared using conventional means for assessing Metropolis-Hastings efficiency, as well as with a novel metric called the conditional acceptance rate for assessing the consequences of using an estimated, and not exact, likelihood. Results indicate the utility of reformulating the model over noise variables, particularly for fast-mixing process models.