Statistical Science

Particle Learning and Smoothing

Carlos M. Carvalho, Michael S. Johannes, Hedibert F. Lopes, and Nicholas G. Polson

Full-text: Open access


Particle learning (PL) provides state filtering, sequential parameter learning and smoothing in a general class of state space models. Our approach extends existing particle methods by incorporating the estimation of static parameters via a fully-adapted filter that utilizes conditional sufficient statistics for parameters and/or states as particles. State smoothing in the presence of parameter uncertainty is also solved as a by-product of PL. In a number of examples, we show that PL outperforms existing particle filtering alternatives and proves to be a competitor to MCMC.

Article information

Statist. Sci. Volume 25, Number 1 (2010), 88-106.

First available in Project Euclid: 3 August 2010

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Mixture Kalman filter parameter learning particle learning sequential inference smoothing state filtering state space models


Carvalho, Carlos M.; Johannes, Michael S.; Lopes, Hedibert F.; Polson, Nicholas G. Particle Learning and Smoothing. Statist. Sci. 25 (2010), no. 1, 88--106. doi:10.1214/10-STS325.

Export citation


  • Briers, M., Doucet, A. and Maskell, S. (2010). Smoothing algorithms for state-space models. Ann. Inst. Statist. Math. 62 61–89.
  • Cappé, O., Godsill, S. and Moulines, E. (2007). An overview of existing methods and recent advances in sequential Monte Carlo. IEEE Proceedings 95 899–924.
  • Carlin, B., Polson, N. G. and Stoffer, D. (1992). A Monte Carlo approach to nonnormal and nonlinear state-space modeling. J. Amer. Statist. Assoc. 87 493–500.
  • Carter, C. and Kohn, R. (1994). On Gibbs sampling for state space models. Biometrika 82 339–350.
  • Carvalho, C. M. and Lopes, H. F. (2007). Simulation-based sequential analysis of Markov switching stochastic volatility models. Comput. Statist. Data Anal. 51 4526–4542.
  • Carvalho, C. M., Lopes, H. F., Polson, N. G. and Taddy, M. (2009). Particle learning for general mixtures. Working paper, Univ. Chicago Booth School of Business.
  • Chen, R. and Liu, J. (2000). Mixture Kalman filters. J. Roy. Statist. Soc. Ser. B 62 493–508.
  • Doucet, A., de Freitas, J. and Gordon, N. (2001). Sequential Monte Carlo Methods in Practice. Springer, New York.
  • Fearnhead, P. (2002). Markov chain Monte Carlo, sufficient statistics, and particle filters. J. Comput. Graph. Statist. 11 848–862.
  • Fearnhead, P., Wyncoll, D. and Tawn, J. (2008). A sequential smoothing algorithm with linear computational cost. Working paper, Dept. Mathematics and Statistics, Lancaster Univ.
  • Frühwirth-Schnatter, S. (1994). Applied state space modelling of non-Gaussian time series using integration-based Kalman filtering. Statist. Comput. 4 259–269.
  • Gamerman, D. and Lopes, H. F. (2006). Markov Chain Monte Carlo: Stochastic Simulation for Bayesian Inference. Chapman & Hall/CRC Press, Boca Raton, FL.
  • Godsill, S. J., Doucet, A. and West, M. (2004). Monte Carlo smoothing for nonlinear time series. J. Amer. Statist. Assoc. 99 156–168.
  • Gordon, N., Salmond, D. and Smith, A. F. M. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings-F 140 107–113.
  • Johannes, M. and Polson, N. G. (2008). Exact particle filtering and learning. Working paper, Univ. Chicago Booth School of Business.
  • Johannes, M., Polson, N. G. and Yae, S. M. (2008). Nonlinear filtering and learning. Working paper, Univ. Chicago Booth School of Business.
  • Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Transactions of the ASME—Journal of Basic Engineering 82 35–45.
  • Liu, J. and Chen, R. (1998). Sequential Monte Carlo methods for dynamic systems. J. Amer. Statist. Assoc. 93 1032–1044.
  • Liu, J. and West, M. (2001). Combined parameters and state estimation in simulation-based filtering. In Sequential Monte Carlo Methods in Practice (A. Doucet, N. de Freitas and N. Gordon, eds.). Springer, New York.
  • Lopes, H. F. and Polson, N. G. (2010). Extracting SP500 and NASDAQ volatility: The credit crisis of 2007–2008. In Handbook of Applied Bayesian Analysis (A. O’Hagan and M. West, eds.) 319–342. Oxford Univ. Press, Oxford.
  • Lopes, H. F. and Tsay, R. E. (2010). Bayesian analysis of financial time series via particle filters. J. Forecast. To appear.
  • Lopes, H. F., Carvalho, C. M., Johannes, M. and Polson, N. G. (2010). Particle learning for sequential Bayesian computation. In Bayesian Statistics 9 (J. M. Bernardo, M. J. Bayarri, J. O. Berger, A. P. Dawid, D. Heckerman, A. F. M. Smith and M. West, eds.). Oxford Univ. Press, Oxford.
  • Papaspiliopoulos, O. and Roberts, G. (2008). Stability of the Gibbs sampler for Bayesian hierarchical models. Ann. Statist. 36 95–117.
  • Pitt, M. and Shephard, N. (1999). Filtering via simulation: Auxiliary particle filters. J. Amer. Statist. Assoc. 94 590–599.
  • Polson, N. G., Stroud, J. and Müller, P. (2008). Practical filtering with sequential parameter learning. J. Roy. Statist. Soc. Ser. B 70 413–428.
  • Prado, R. and Lopes, H. F. (2010). Sequential parameter learning and filtering in structured autoregressive models. Working paper, Univ. Chicago Booth School of Business.
  • Storvik, G. (2002). Particle filters in state space models with the presence of unknown static parameters. IEEE Trans. Signal Process. 50 281–289.
  • West, M. (1986). Bayesian model monitoring. J. Roy. Statist. Soc. Ser. B 48 70–78.
  • West, M. and Harrison, J. (1997). Bayesian Forecasting and Dynamic Models, 2nd ed. Springer, New York.