Bayesian Analysis

Application of Girsanov theorem to particle filtering of discretely observed continuous-time non-linear systems

Tommi Sottinen and Simo Särkkä

Full-text: Open access

Abstract

This article considers the application of particle filtering to continuous-discrete optimal filtering problems, where the system model is a stochastic differential equation, and noisy measurements of the system are obtained at discrete instances of time. It is shown how the Girsanov theorem can be used for evaluating the likelihood ratios needed in importance sampling. It is also shown how the methodology can be applied to a class of models, where the driving noise process is lower in the dimensionality than the state and thus the laws of the state and the noise are not absolutely continuous. Rao-Blackwellization of conditionally Gaussian models and unknown static parameter models is also considered.

Article information

Source
Bayesian Anal. Volume 3, Number 3 (2008), 555-584.

Dates
First available in Project Euclid: 22 June 2012

Permanent link to this document
https://projecteuclid.org/euclid.ba/1340370438

Digital Object Identifier
doi:10.1214/08-BA322

Mathematical Reviews number (MathSciNet)
MR2434403

Zentralblatt MATH identifier
1330.93230

Keywords
Girsanov theorem particle filtering continuous-discrete filtering

Citation

Särkkä, Simo; Sottinen, Tommi. Application of Girsanov theorem to particle filtering of discretely observed continuous-time non-linear systems. Bayesian Anal. 3 (2008), no. 3, 555--584. doi:10.1214/08-BA322. https://projecteuclid.org/euclid.ba/1340370438.


Export citation