Abstract
As a popular nonlinear estimation tool, the sampling importance resampling (SIR) filter has been applied with the expectation–maximization (EM) principle, including the typical maximum a posteriori (MAP) estimation and maximum likelihood (ML) estimation, for estimating the parameters of the state space model (SSM). This paper concentrates on an inevitable bias existing in the EM-SIR filter for estimating the dynamics process of the SSM. It is analyzed that the root reason for the bias is the sample impoverishment caused by the resampling procedure employed in the filter. A process noise simulated for the particle propagation that is larger than the real noise involved with the true state will be helpful to counteract sample impoverishment, thereby providing better filtering result. Correspondingly, the EM-SIR filter tends to yield a biased (larger-than-the-truth) estimate of the process noise if it is unknown and needs to be estimated. The bias is elaborated via a straightforward roughening approach by means of both qualitative logical deduction and quantitative numerical simulation. However, it seems hard to fully remove this bias in practice.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Storvik, G.: Particle filter for state-space models with the presence of unknown static parameters. IEEE Transactions on Signal Processing 50(2), 281–289 (2002)
Schön, T.B., Wills, A., Ninness, B.: identification of nonlinear state-space models. Automatica 47(1), 39–49 (2011)
Doucet, A., Tadic, V.B.: Parameter estimation in general state-space models using particle methods. Annals of the Institute of Statistical Mathematics 55, 409–422 (2003)
Yildirim, S., Jiang, L., Singh, S.S., Dean, T.A.: Calibrating the Gaussian multi-target tracking model. Statistics and Computing, 1–14 (2014)
Dean, T.A., Singh, S.S., Jasra, A., Peters, G.W.: Parameter estimation for hidden Markov models with intractable likelihoods. Scand. J. Statist. 41, 970–987 (2014)
Lundquist, C., Karlsson, R., Ozkan, E., Gustafsson, F.: Tire radii estimation using a marginalized particle filter. IEEE Transactions on Intelligent Transportation Systems 15(2), 663–672 (2014)
Zikmundová, M., Helisová, K.S., Beneš, V.: On the use of particle Markov Chain Monte Carlo in parameter estimation of space-time interacting discs. Methodology and Computing in Applied Probability 16(2), 451–463 (2014)
Andrieu, C., Doucet, A., Tadic, V.B.: Online parameter estimation in general state-space models. In: Proc. IEEE CDC/ECC, Seville, Spain, pp. 332–337 (2005)
Poyiadjis, G., Doucet, A., Singh, S.S.: Parameter approximations of the score and observed information matrix in state space models with application to parameter estimation. Biometrika 98, 65–80 (2011)
Kantas, N., Doucet, A., Singh, S.S., Maciejowski, J.M., Chopin, N.: On particle methods for parameter estimation in state-space models. Statistical Science (2015)
Olsson, J., Cappe, O., Douc, R., Moulines, E.: SMC Smoothing with application to parameter estimation in nonlinear state-space models. Bernoulli 14(1), 155–179 (2008)
Li, T., Sun, S., Sattar, T.P., Corchado, J.M.: Fight sample degeneracy and impoverishment in particle filters: A review of intelligent approaches. Expert Systems with Applications 41(8), 3944–3954 (2014)
Li, T., Bolic, M., Djuric, P.: Resampling methods for particle filtering, IEEE Signal Processing Magazine (to appear, May 2015), doi:10.1109/MSP.2014.2330626
Poyiadjis, G., Doucet, A., Singh, S.S.: Maximum likelihood parameter estimation in general state-space models using particle methods. In: Proc. American Stat. Assoc. (2005)
Hong, M., Bugallo, M.F., Djurić, P.M.: Joint model selection and parameter estimation by population Monte Carlo simulation. Journal of Selected Topics in Signal Processing 4(3), 526–539 (2010)
MĂguez, J., Crisan, D., Djurić, P.M.: On the use of sequential Monte Carlo methods for maximum a posteriori sequence estimation and stochastic global optimization. Statistics and Computing 23(1), 91–107 (2013)
Liu, J., West, M.: Combined parameters and state estimation in simulation based filtering. In: Doucet, A., de Freitas, N., Gordon, N. (eds.) Sequential Monte Carlo Methods in Practice, pp. 197–223. Springer, New York (2001)
Carvalho, C.M., Johannes, M., Lopes, H.F., Polson, N.: Particle learning and smoothing. Statistical Science 25(1), 88–106 (2010)
Lopes, H.F., Tsay, R.S.: Particle filters and Bayesian inference in financial econometrics. J. Forecasting 30, 168–209 (2011)
Li, T., Sattar, T.P., Han, Q., Sun, S.: Roughening methods to prevent sample impoverishment in the particle PHD filter. In: 16th International Conference on Information Fusion, Istanbul, Turkey, July 10-12 (2013)
Gordon, N., Salmond, D., Smith, A.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc. F Radar Signal Processing 140(2), 107–113 (1993)
Fulop, A., Li, J.: Efficient Learning via Simulation: A marginalized resample-move approach. Journal of Econometrics 176, 146–161 (2013)
Li, T., Corchado, J.M., Bajo, J., Sun, S., De Paz, J.F.: Do we always need a filter, arXiv:1408.4636 [stat.AP]
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, T., RodrĂguez, S., Bajo, J., Corchado, J.M., Sun, S. (2015). On the Bias of the SIR Filter in Parameter Estimation of the Dynamics Process of State Space Models. In: Omatu, S., et al. Distributed Computing and Artificial Intelligence, 12th International Conference. Advances in Intelligent Systems and Computing, vol 373. Springer, Cham. https://doi.org/10.1007/978-3-319-19638-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-19638-1_10
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19637-4
Online ISBN: 978-3-319-19638-1
eBook Packages: EngineeringEngineering (R0)