Unbiased Parameter Inference for a Class of Partially Observed Levy-Process Models

TL;DR

This paper introduces an unbiased Bayesian inference method for partially observed Levy-process models, enabling accurate parameter estimation without discretization bias, and demonstrates its efficiency on financial data.

Contribution

The paper presents a novel unbiased inference approach for Levy-process models that improves accuracy and computational efficiency over existing methods.

Findings

Method is unbiased and parallelizable.

Applied successfully to S&P 500 data.

Outperforms some MCMC algorithms in efficiency.

Abstract

We consider the problem of static Bayesian inference for partially observed Levy-process models. We develop a methodology which allows one to infer static parameters and some states of the process, without a bias from the time-discretization of the afore-mentioned Levy process. The unbiased method is exceptionally amenable to parallel implementation and can be computationally efficient relative to competing approaches. We implement the method on S & P 500 log-return daily data and compare it to some Markov chain Monte Carlo (MCMC) algorithm.