Martingale Posteriors for Discretely Observed Diffusions

TL;DR

This paper introduces a new martingale posterior method for estimating parameters of discretely observed diffusion processes, offering faster computation with quantifiable uncertainty, especially when transition densities are approximated numerically.

Contribution

The paper develops a martingale posterior approach that approximates the true posterior with minimal time-discretization bias, providing a computationally efficient alternative to MCMC methods.

Findings

The method achieves significant speed-ups compared to state-of-the-art MCMC algorithms.

It approximates the martingale posterior with bias of order $ ext{O}( riangle)$.

Illustrations show orders of magnitude faster performance.

Abstract

In this paper we consider parameter estimation for discretely observed diffusion processes. In particular, we focus on data that are observed at low frequency and methodology that can estimate parameters with uncertainty quantification. Most statistical work in this domain develops advanced Markov chain Monte Carlo (MCMC) algorithms for sampling from the posterior of the parameters, a task which is often complicated by the fact that one seldom has access to the transition density of the diffusion process; one has to combine sophisticated MCMC methods which are robust to the required time discretization of the diffusion, which can yield expensive algorithms. We focus on developing the martingale posterior method for the context of interest, when one can only numerically approximate the transition density of the diffusion. Based on using types of diffusion bridges we introduce a new martingale posterior method for parameter estimation for discretely observed diffusion processes. We prove that this algorithm approximates, in some sense, the martingale posterior which has no time-discretization bias up-to $\mathcal{O}(\Delta)$ if $\Delta$ is the time discretization step. Our approach is illustrated on several examples, showing orders of magnitude speed up versus state-of-the-art MCMC algorithms.