The Library

A note on auxiliary particle filters

Tools

Johansen, Adam M. and Doucet, Arnaud. (2008) A note on auxiliary particle filters. Statistics & Probability Letters, Vol.78 (No.12). pp. 1498-1504. ISSN 01677152

Preview

PDF
WRAP_Johansen_JD08.pdf - Submitted Version - Requires a PDF viewer.
Download (212Kb)

Official URL: http://dx.doi.org/10.1016/j.spl.2008.01.032

Abstract

The Auxiliary Particle Filter (APF) introduced by Pitt and Shephard (1999) is a
very popular alternative to Sequential Importance Sampling and Resampling (SISR)
algorithms to perform inference in state-space models. We propose a novel interpretation of the APF as an SISR algorithm. This interpretation allows us to present
simple guidelines to ensure good performance of the APF and the first convergence
results for this algorithm. Additionally, we show that, contrary to popular belief,
the asymptotic variance of APF-based estimators is not always smaller than those
of the corresponding SISR estimators – even in the ‘perfect adaptation’ scenario.

Item Type:

Journal Article

Subjects:

Q Science > QA Mathematics

Divisions:

Faculty of Science > Statistics

Library of Congress Subject Headings (LCSH):

Filters (Mathematics), State-space methods, Inference

Journal or Publication Title:

Statistics & Probability Letters

Publisher:

Elsevier Science BV

ISSN:

01677152

Official Date:

1 September 2008

Dates:

Date	Event
1 September 2008	Published

Volume:

Vol.78

Number:

No.12

Page Range:

pp. 1498-1504

Identifier:

10.1016/j.spl.2008.01.032

Status:

Peer Reviewed

Access rights to Published version:

Restricted or Subscription Access

References:

[1] Carpenter, J., Clifford, P. and Fearnhead, P. (1999) An improved particle filter
for non-linear problems. IEE proceedings - Radar, Sonar and Navigation, 146,
2-7.
[2] Chopin, N. (2004) Central limit theorem for sequential Monte Carlo and its
application to Bayesian inference. Ann. Statist., 32, 2385-2411.
[3] Del Moral, P. (2004) Feynman-Kac Formulae: Genealogical and Interacting
Particle Systems with Applications, Series Probability and Applications, New
York: Springer-Verlag.
[4] Del Moral, P., Doucet, A. and Peters, G.W. (2007) Sharp propagation of
chaos estimates for Feynman-Kac particle models. Theory of Probability and
Its Applications 51, 459-485.
[5] Doucet, A., Godsill, S.J. and Andrieu, C. (2000) On sequential Monte Carlo
sampling methods for Bayesian filtering. Statistics and Computing, 10, 197-
208.
[6] Doucet, A., de Freitas, J.F.G. and Gordon, N.J. (eds.) (2001) Sequential Monte
Carlo Methods in Practice. New York: Springer-Verlag.
[7] Fearnhead, P., Papaspiliopoulos, O. and Roberts, G.O. (2007) Particle filters
for partially-observed diffusions. Technical report, Lancaster University.
[8] Godsill, S.J. and Clapp, T. (2001) Improvement strategies for Monte Carlo
particle filters, in [6], 139-158.
[9] Johansen, A.M. (2006) Some non-standard sequential Monte Carlo methods and
their applications. PhD Thesis, Cambridge University.
[10] Johansen, A.M. and Doucet, A. (2007) Auxiliary variable sequential Monte
Carlo methods. Statistics Group Technical Report, 07:09, University of Bristol.
http://www.stats.bris.ac.uk/research/stats/reports/2007/
[11] Liu, J.S. (2001) Monte Carlo Strategies in Scientific Computing. New York:
Springer-Verlag.
[12] Pitt, M.K. and Shephard, N. (1999). Filtering via simulation: auxiliary particle
filters. J. Am. Statist. Ass., 94, 590-599.
[13] Pitt, M.K. and Shephard, N. (2001). Auxiliary variable based particle filters, in
[6], 271–293.