Parameter Estimation in General State-Space Models using Particle Methods

Authors: Doucet A.¹; Tadi cacute V.B.²

Source: Annals of the Institute of Statistical Mathematics, Volume 55, Number 2, 2003 , pp. 409-422(14)

Publisher: Springer

Buy & download fulltext article:

Price: $47.00 plus tax (Refund Policy)

Abstract:

Particle filtering techniques are a set of powerful and versatile simulation-based methods to perform optimal state estimation in nonlinear non-Gaussian state-space models. If the model includes fixed parameters, a standard technique to perform parameter estimation consists of extending the state with the parameter to transform the problem into an optimal filtering problem. However, this approach requires the use of special particle filtering techniques which suffer from several drawbacks. We consider here an alternative approach combining particle filtering and gradient algorithms to perform batch and recursive maximum likelihood parameter estimation. An original particle method is presented to implement these approaches and their efficiency is assessed through simulation.

Keywords: Optimal filtering; parameter estimation; sequential Monte Carlo; state-space models; stochastic approximation

Document Type: Research article

Affiliations: 1: Signal Processing Group, Department of Engineering, Cambridge University, Trumpington Street, CB2 1PZ Cambridge, U.K., Email: ad2@eng.cam.ac.uk 2: Department of Electrical and Electronic Engineering, University of Melbourne, Parkville, Victoria 3010, Australia, Email: v.tadic@ee.mu.oz.au

Publication date: 2003-01-01