Robust Time Series Estimation via Weighted Likelihood

  • C. Agostinelli
Conference paper

Summary

In this paper we introduce a method for efficient and robust estimation of the unknown parameters of an autoregressive-moving average model based on weighted likelihood. Two types of outliers, i.e. additive and innovation, are taken into account without knowing their number, position or intensity. A new procedure is used to classify the outliers and to bound the impact of additive outliers in order to improve the breakdown point of the method. Two examples and a Monte Carlo simulation are presented.

Key words

Additive outliers Autoregressive-moving average model Innovation outliers Robust estimation Weighted likelihood 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. C. Agostinelli. A one-step robust estimator based on the weighted likelihood methodology. Working paper 1997.16, Department of Statistics, University of Padua, 1997.Google Scholar
  2. C. Agostinelli. Inferenza statistica robusta basata sulla funzione di verosimiglianza pesata: alcuni sviluppi. PhD thesis, Dipartimento di Scienze Statistiche, Università di Padova, 1998.Google Scholar
  3. C. Agostinelli. Metodi robusti per la selezione di modelli. XL Riunione Scientifica della Società Italiana di Statistica, Firenze, 2000.Google Scholar
  4. C. Agostinelli and M. Markatou. Tests of hypotheses based on the weighted likelihood methodology. Statistica Sinica, 11(2):499–514, 2001.MathSciNetMATHGoogle Scholar
  5. A. Azzalini Maximum likelihood estimation of order m for stationary stochastic processes. Biometrika, 70:381–387, 1983.MathSciNetCrossRefGoogle Scholar
  6. V. Barnett and L. Toby. Outliers in statistical data. Wiley, New York, 3rd edition, 1994.MATHGoogle Scholar
  7. P.J. Brockwell and R.A. Davis. Time series: Theory and methods. Springer, New York, 2nd edition, 1991.CrossRefGoogle Scholar
  8. O.H. Bustos and V.J. Yohai. Robust estimates of ARMA models. J. Am. Statist. Assoc.,81: 155–169, 1986.MathSciNetCrossRefGoogle Scholar
  9. C. Chen and L. Liu. Joint estimation of model parameters and outlier effects in time series. J. Am. Statist. Assoc., 88:284–297, 1993.MATHGoogle Scholar
  10. T. Flak, W. Schmid, and R. Sigmund. A comparison of severals procedures for identifying outliers in contaminated ARMA processes. Computational Statistics, 11:175–195, 1996.MathSciNetMATHGoogle Scholar
  11. A.J. Fox. Outliers in time series. J. Royal Statist. Soc., 34, Series B:350–363, 1972.MATHGoogle Scholar
  12. P.H. Franses and A. Lucas. Outliers robust cointegration analysis. Report 9529 A, Erasmus University, Rotterdam, 1995.Google Scholar
  13. R. Ihaka and R. Gentleman. A language for data analysis and graphics. J. Computational and Graphical Statistics, 5:299–314, 1996.Google Scholar
  14. B.G. Lindsay. Efficiency versus robustness: the case for minimum Hellinger distance and related methods. Ann. Statist., 22:1018–1114, 1994.MathSciNetCrossRefGoogle Scholar
  15. G.S. Maddala and Y. Yin. Outliers, unit roots and robust estimation of nonstationary time series. In G.S. Maddala and C.R. Rao, editors, Handbook of Statistics, chapter 15, pages 237–266. Elsevier, 1997.Google Scholar
  16. M. Markatou. Robust statistical inference: Weighted likelihoods or usual M-estimation? Comm. Statist., Theory Meth., 25:2597–2613, 1996.MathSciNetMATHCrossRefGoogle Scholar
  17. M. Markatou, A. Basu, and B.G. Lindsay. Weighted likelihood estimating equations: The discrete case with applications to logistic regression. J. Statist. Planning and Inf.,57: 215–232, 1997.MathSciNetMATHCrossRefGoogle Scholar
  18. M. Markatou, A. Basu, and B.G. Lindsay. Weighted likelihood estimating equations with a bootstrap root search. J. Am. Statist. Assoc., 93:740–750, 1998.MathSciNetMATHCrossRefGoogle Scholar
  19. R.D. Martin. Robust estimation of autoregressive models. In D.R. Brillinger and G.C. Tiao, editors, Directions in Time Series, pages 228–254. Institute of Mathematical Statistics, Hayward, CA, 1980.Google Scholar
  20. R.D. Martin. Robust methods for time series. In D.F. Findley, editor, Applied Times Series Analysis II, chapter Time series, pages 683–759. Academic Press, New York, 1981.Google Scholar
  21. R.D. Martin and V.J. Yohai. Robustness in time series and estimating ARMA models. In E.J. Hannan, D.R. Brillinger, and P.R. Krishnaiah, editors, Handbook of Statistics, chapter 5, pages 119–155. Elsevier, 1985.Google Scholar
  22. G. Masarotto. Robust and consistent estimates of autoregressive-moving average parameters. Biometrika, 74:791–797, 1987.MathSciNetMATHCrossRefGoogle Scholar
  23. W. Schmid. Discussion of a LR test for detecting outliers in time series data. Statistics and Decisions, 8:271–294, 1990.MathSciNetMATHGoogle Scholar
  24. W. Schmid. How to locate outliers in a time series, if a starting-block is present. Sankhya,Series B, 53:359–383, 1991.MATHGoogle Scholar
  25. W. Schmid. An outlier test for time series based on a two-sided predictor. J. of Time Series Analysis, 17:497–510, 1996.MATHCrossRefGoogle Scholar
  26. R.S. Tsay. Time series model specification in the presence of outliers. J. Am. Statist. Assoc.,81:132–141, 1986.CrossRefGoogle Scholar
  27. R.S. Tsay. Outliers, level shifts and variance changes in time series. J. of Forecasting, 7: 1–20, 1988.CrossRefGoogle Scholar
  28. K. Vaage. Detection of outliers and level shifts in time series: an evaluation of two alternative procedures. J. of Forecasting, 19:23–27, 2000.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • C. Agostinelli
    • 1
  1. 1.Department of StatisticsUniversity of VeneziaItaly

Personalised recommendations