Statistics and Computing

, Volume 23, Issue 1, pp 43–57 | Cite as

Sequential parameter learning and filtering in structured autoregressive state-space models

Article

Abstract

We present particle-based algorithms for sequential filtering and parameter learning in state-space autoregressive (AR) models with structured priors. Non-conjugate priors are specified on the AR coefficients at the system level by imposing uniform or truncated normal priors on the moduli and wavelengths of the reciprocal roots of the AR characteristic polynomial. Sequential Monte Carlo algorithms are considered and implemented for on-line filtering and parameter learning within this modeling framework. More specifically, three SMC approaches are considered and compared by applying them to data simulated from different state-space AR models. An analysis of a human electroencephalogram signal is also presented to illustrate the use of the structured state-space AR models in describing biomedical signals.

Keywords

State-space autoregressions Structured priors Sequential filtering and parameter learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Cappé, O., Godsill, S., Moulines, E.: An overview of existing methods and recent advances in sequential Monte Carlo. IEEE Proc. Signal Process. 95, 899–924 (2007) Google Scholar
  2. Carter, C., Kohn, R.: Gibbs sampling for state space models. Biometrika 81, 541–553 (1994) MathSciNetMATHCrossRefGoogle Scholar
  3. Carvalho, C., Johannes, M., Lopes, H., Polson, N.: Particle learning and smoothing. Stat. Sci. 25, 88–106 (2010) MathSciNetCrossRefGoogle Scholar
  4. Chopin, N., Jacob, P.E., Papaspiliopoulos, O.: SMC2: A sequential Monte Carlo algorithm with particle Markov chain Monte Carlo updates. Technical report, ENSAE-CREST (2011) Google Scholar
  5. Del Moral, P., Doucet, A., Jasra, A.: Sequential Monte Carlo samplers. J. R. Stat. Soc. B 68, 411–436 (2006) MATHCrossRefGoogle Scholar
  6. Doucet, A., Johansen, A.M.: A tutorial on particle filtering and smoothing: Fifteen years later. In: Crisan, D., Rozovsky, B. (eds.) Oxford Handbook of Nonlinear Filtering. Oxford University Press, London (2011) Google Scholar
  7. Fearnhead, P.: MCMC, sufficient statistics and particle filter. J. Comput. Graph. Stat. 11, 848–862 (2002) MathSciNetCrossRefGoogle Scholar
  8. Flury, T., Shephard, N.: Learning and filtering via simulation: smoothly jittered particle filters. Technical report, Oxford-Man Institute (2009) Google Scholar
  9. Frühwirth-Schnatter, S.: Data augmentation and dynamic linear models. J. Time Ser. Anal. 15, 183–202 (1994) MathSciNetMATHCrossRefGoogle Scholar
  10. Granger, C., Morris, M.J.: Time series modelling and interpretation. J. R. Stat. Soc. A 139(2), 246–257 (1976) MathSciNetCrossRefGoogle Scholar
  11. Huerta, G., West, M.: Bayesian inference on periodicities and component spectral structure in time series. J. Time Ser. Anal. 20, 401–416 (1999a) MathSciNetMATHCrossRefGoogle Scholar
  12. Huerta, G., West, M.: Priors and component structures in autoregressive time series models. J. R. Stat. Soc. B 61, 881–899 (1999b) MathSciNetMATHCrossRefGoogle Scholar
  13. Liu, J., West, M.: Combined parameter 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, Berlin (2001) Google Scholar
  14. Liu, J.S.: Metropolized independent sampling with comparisons to rejection sampling and importance sampling. Stat. Comput. 6, 113–119 (1996) CrossRefGoogle Scholar
  15. Lopes, H.F., Polson, N.G.: Particle learning for fat-tailed distributions. Technical report, The University of Chicago Booth School of Business (2010) Google Scholar
  16. Lopes, H.F., Tsay, R.S.: Particle filters and Bayesian inference in financial econometrics. J. Forecast. 30, 168–209 (2011) MathSciNetMATHCrossRefGoogle Scholar
  17. Lopes, H.F., Carvalho, C.M., Johannes, M., Polson, N.G.: Particle learning for sequential Bayesian computation (with discussion). In: Bernardo, J.M., Bayarri, M.J., Berger, J.O., Dawid, A.P., Heckerman, D., Smith, A.F.M., West, M. (eds.) Bayesian Statistics 9, pp. 317–360. Oxford University Press, Oxford (2010) Google Scholar
  18. Pitt, M., Shephard, N.: Filtering via simulation: Auxiliary variable particle filters. J. Am. Stat. Assoc. 94, 590–599 (1999) MathSciNetMATHCrossRefGoogle Scholar
  19. Poyiadjis, G., Doucet, A., Singh, S.S.: Particle approximations of the score and observed information matrix in state space models with application to parameter estimation. Biometrika 98, 65–80 (2011) MathSciNetMATHCrossRefGoogle Scholar
  20. Prado, R.: Characterization of latent structure in brain signals. In: Chow, S., Ferrer, E., Hsieh, F. (eds.) Statistical Methods for Modeling Human Dynamics, pp. 123–153. Routledge, Taylor and Francis, New York (2010a) Google Scholar
  21. Prado, R.: Multi-state models for mental fatigue. In: O’Hagan, A., West, M. (eds.) The Handbook of Applied Bayesian Analysis. Oxford University Press, Oxford (2010b) Google Scholar
  22. Prado, R., West, M.: Time Series: Modeling, Computation, and Inference. CRC Press, Chapman & Hall, Boca Raton (2010) MATHGoogle Scholar
  23. Prado, R., West, M., Krystal, A.: Multi-channel EEG analyses via dynamic regression models with time-varying lag/lead structure. J. R. Stat. Soc., Ser. C, Appl. Stat. 50, 95–109 (2001) CrossRefGoogle Scholar
  24. Storvik, G.: Particle filters for state-space models with the presence of unknown static parameters. IEEE Trans. Signal Process. 50, 281–289 (2002) MathSciNetCrossRefGoogle Scholar
  25. West, M.: Approximating posterior distributions by mixtures. J. R. Stat. Soc. B 55, 409–422 (1993) MATHGoogle Scholar
  26. West, M.: Time series decomposition. Biometrika 84, 489–494 (1997) MATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.Department of Applied Mathematics and Statistics, Baskin School of EngineeringUniversity of California Santa CruzSanta CruzUSA
  2. 2.University of Chicago Booth School of BusinessChicagoUSA

Personalised recommendations