On particle methods for parameter estimation in state-space models

Published version
Repository DOI

Change log
Kantas, N 
Doucet, A 
Singh, SS 
Chopin, N 

Nonlinear non-Gaussian state-space models are ubiquitous in statistics, econometrics, information engineering and signal processing. Particle methods, also known as Sequential Monte Carlo (SMC) methods, provide reliable numerical approximations to the associated state inference problems. However, in most applications, the state-space model of interest also depends on unknown static parameters that need to be estimated from the data. In this context, standard particle methods fail and it is necessary to rely on more sophisticated algorithms. The aim of this paper is to present a comprehensive review of particle methods that have been proposed to perform static parameter estimation in state-space models. We discuss the advantages and limitations of these methods and illustrate their performance on simple models.


This is the final version of the article. It first appeared from Institute of Mathematical Statistics via http://projecteuclid.org/euclid.ss/1439220716.

Bayesian inference, maximum likelihood inference, particle filtering, Sequential Monte Carlo, state-space models
Journal Title
Statistical Science
Conference Name
Journal ISSN
Volume Title
Institute of Mathematical Statistics
Engineering and Physical Sciences Research Council (EP/G037590/1)
N. Kantas was supported by the Engineering and Physical Sciences Research Council (EPSRC) under grant EP/J01365X/1 and programme grant on Control For Energy and Sustainability (EP/G066477/1). S.S. Singh's research is partly funded by EPSRC under the First Grant Scheme (EP/G037590/1). A. Doucet's research is partly funded by EPSRC (EP/K000276/1 and EP/K009850/1). N. Chopin's research is partly by the ANR as part of the "Investissements d'Avenir" program (ANR-11-LABEX-0047).