Statistics and Computing

, Volume 25, Issue 2, pp 365–374 | Cite as

Retrospective Bayesian outlier detection in INGARCH series

  • Roland Fried
  • Inoncent Agueusop
  • Björn Bornkamp
  • Konstantinos Fokianos
  • Jana Fruth
  • Katja Ickstadt
Article

Abstract

INGARCH models for time series of counts arising, e.g., in epidemiology or finance assume the observations to be Poisson distributed conditionally on the past, with the conditional mean being an affine-linear function of the previous observations and the previous conditional means. We model outliers within such processes, assuming that we observe a contaminated process with additive Poisson distributed contamination, affecting each observation with a small probability. Our particular concern are additive outliers, which do not enter the dynamics of the process and can represent measurement artifacts and other singular events influencing a single observation. Retrospective analysis of such outliers is difficult within a non-Bayesian framework since the uncontaminated values entering the dynamics of the process at contaminated time points are unobserved. We propose a Bayesian approach to outlier modeling in INGARCH processes, approximating the posterior distribution of the model parameters by application of a componentwise Metropolis-Hastings algorithm. Analyzing real and simulated data sets, we find Bayesian outlier detection with non-informative priors to work well in practice when there are some outliers in the data.

Keywords

Generalized linear models Time series of counts Additive outliers 

References

  1. Abanto-Valle, C.A., Bandyopadhyay, D., Lachos, V.H., Enriquez, I.: Robust Bayesian analysis of heavy-tailed stochastic volatility models using scale mixtures of normal distributions. Comput. Stat. Data Anal. 54, 2883–2898 (2010) CrossRefMATHMathSciNetGoogle Scholar
  2. Atchadé, Y.F., Liu, J.: The Wang-Landau algorithm in general state spaces: applications and convergence analysis. Stat. Sin. 20, 209–233 (2010) MATHGoogle Scholar
  3. Bollerslev, T.: Generalized autoregressive conditional heteroskedasticity. J. Econom. 31, 307–327 (1986) CrossRefMATHMathSciNetGoogle Scholar
  4. Charles, A., Darne, O.: Outliers and GARCH models in financial data. Econ. Lett. 86, 347–352 (2005) CrossRefMATHMathSciNetGoogle Scholar
  5. Chen, C., Liu, L.M.: Joint estimation of model parameters and outlier effects in time series. J. Am. Stat. Assoc. 88, 284–297 (1993) MATHGoogle Scholar
  6. Cox, D.R.: Statistical analysis of time series: some recent developments. Scand. J. Stat. 8, 93–115 (1981) MATHGoogle Scholar
  7. Davies, P.L., Gather, U.: The identification of multiple outliers (with discussion and reply). J. Am. Stat. Assoc. 88, 782–801 (1993) CrossRefMATHMathSciNetGoogle Scholar
  8. Doukhan, P., Fokianos, K., Tjostheim, D.: On weak dependence conditions for Poisson autoregressions. Stat. Probab. Lett. 82, 942–948 (2012) CrossRefMATHMathSciNetGoogle Scholar
  9. Ferland, R., Latour, A., Oraichi, D.: Integer-valued GARCH process. J. Time Ser. Anal. 27, 923–942 (2006) CrossRefMATHMathSciNetGoogle Scholar
  10. Fokianos, K.: Some recent progress in count time series. Statistics 45, 49–58 (2012) CrossRefMathSciNetGoogle Scholar
  11. Fokianos, K., Fried, R.: Interventions in INGARCH processes. J. Time Ser. Anal. 31, 210–225 (2010) CrossRefMATHMathSciNetGoogle Scholar
  12. Fokianos, K., Rahbek, A., Tjostheim, D.: Poisson autoregression. J. Am. Stat. Assoc. 104, 1430–1439 (2009) CrossRefMATHMathSciNetGoogle Scholar
  13. Fox, A.J.: Outliers in time series. J. R. Stat. Soc. B 34, 350–363 (1972) MATHGoogle Scholar
  14. Heinen, A.: Modelling time series count data: an autoregressive conditional Poisson model. MPRA Paper 8113, University Library of Munich, Germany (2003). Available at http://mpra.ub.uni-muenchen.de/8113/
  15. Justel, A., Peña, D., Tsay, R.S.: Detection of outlier patches in autoregressive time series. Stat. Sin. 11, 651–673 (2001) MATHGoogle Scholar
  16. Lunn, D., Spiegelhalter, D., Thomas, A., Best, N.: The BUGS project: evolution, critique, and future directions. Stat. Med. 28, 3049–3067 (2009) CrossRefMathSciNetGoogle Scholar
  17. Neal, R.M.: MCMC using Hamiltonian dynamics. In: Brooks, S., Gelman, A., Jones, G.L., Meng, X.-L. (eds.) Handbook of Markov Chain Monte Carlo, pp. 113–162. Chapman & Hall/CRC Press, New York (2010) Google Scholar
  18. Ntzoufras, I.: Bayesian Modeling Using WinBUGS. Wiley, New York (2009) CrossRefMATHGoogle Scholar
  19. O’Hagan, A., Murphy, T.B., Gormley, I.C.: Computational aspects of fitting mixture models via the expectation-maximization algorithm. Comput. Stat. Data Anal. 56, 3843–3864 (2012) CrossRefMATHMathSciNetGoogle Scholar
  20. R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2009). ISBN 3-900051-07-0 Google Scholar
  21. Rigaill, G., Lebarbier, E., Robin, S.: Exact posterior distributions and model selection criteria for multiple change-point detection problems. Stat. Comput. 22, 917–929 (2012) CrossRefMATHMathSciNetGoogle Scholar
  22. Rydberg, T.H., Shephard, N.: A modelling framework for the prices and times of trades made on the New York stock exchange. In: Fitzgerald, W.J., Smith, R.L., Walden, A.T., Young, P.C. (eds.) Nonlinear and Nonstationary Signal Processing, pp. 217–246. Isaac Newton Institute and Cambridge University Press, Cambridge (2000) Google Scholar
  23. Silva, M.E., Frias, R., Pereira, I.: Detection of additive outliers in Poisson INteger-valued AutoRegressive time series (2012). Available at http://arxiv.org/pdf/1204.6516.pdf
  24. Streett, S.: Some observation driven models for time series of counts. PhD-thesis, Colorado State University, Department of Statistics (2000) Google Scholar
  25. Sturtz, S., Ligges, U., Gelman, A.: R2WinBUGS: a package for running WinBUGS from R. J. Stat. Softw. 12, 1–16 (2005) Google Scholar
  26. Unnikrishnan, N.K.: Bayesian analysis for outliers in survey sampling. Comput. Stat. Data Anal. 54, 1962–1974 (2010) CrossRefMATHMathSciNetGoogle Scholar
  27. Wang, J.J., Chan, J.S.K., Choy, S.T.B.: Stochastic volatility models with leverage and heavy-tailed distributions: a Bayesian approach using scale mixtures. Comput. Stat. Data Anal. 55, 852–862 (2011) CrossRefMATHMathSciNetGoogle Scholar
  28. West, M., Harrison, P.J.: Bayesian Forecasting & Dynamic Models, 2nd edn. Springer, New York (1997) MATHGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Roland Fried
    • 1
  • Inoncent Agueusop
    • 1
  • Björn Bornkamp
    • 2
  • Konstantinos Fokianos
    • 3
  • Jana Fruth
    • 1
  • Katja Ickstadt
    • 1
  1. 1.TU Dortmund UniversityDortmundGermany
  2. 2.NovartisBaselSwitzerland
  3. 3.University of CyprusNicosiaCyprus

Personalised recommendations