The Annals of Statistics

Robust estimation for ARMA models

Nora Muler, Daniel Peña, and Víctor J. Yohai

Full-text: Open access

Abstract

This paper introduces a new class of robust estimates for ARMA models. They are M-estimates, but the residuals are computed so the effect of one outlier is limited to the period where it occurs. These estimates are closely related to those based on a robust filter, but they have two important advantages: they are consistent and the asymptotic theory is tractable. We perform a Monte Carlo where we show that these estimates compare favorably with respect to standard M-estimates and to estimates based on a diagnostic procedure.

Article information

Source
Ann. Statist., Volume 37, Number 2 (2009), 816-840.

Dates
First available in Project Euclid: 10 March 2009

Permanent link to this document
https://projecteuclid.org/euclid.aos/1236693151

Digital Object Identifier
doi:10.1214/07-AOS570

Mathematical Reviews number (MathSciNet)
MR2502652

Zentralblatt MATH identifier
1162.62405

Subjects
Primary: 62F35: Robustness and adaptive procedures 62M10: Time series, auto-correlation, regression, etc. [See also 91B84]

Keywords
MM-estimates outliers time series

Citation

Muler, Nora; Peña, Daniel; Yohai, Víctor J. Robust estimation for ARMA models. Ann. Statist. 37 (2009), no. 2, 816--840. doi:10.1214/07-AOS570. https://projecteuclid.org/euclid.aos/1236693151


Export citation

References

  • [1] Bianco, A. M., Garcia Ben, M., Martinez, E. and Yohai, V. J. (1996). Robust procedures for regression models with ARIMA errors. In COMPSTAT 96. Proceeding of Computational Statistics (A. Prat, ed.) 27–38. Physica-Verlag, Heidelberg.
  • [2] Brubacher, S. R. (1974). Time series outlier detection and modeling with interpolation. Bell Laboratories Technical Memo.
  • [3] Bustos, O. H. and Yohai, V. J. (1986). Robust estimates for ARMA models. J. Amer. Statist. Assoc. 81 155–168.
  • [4] Chang, I., Tiao, G. C. and Chen, C. (1988). Estimation of time series parameters in the presence of outliers. Technometrics 30 193–204.
  • [5] Chen, C. and Liu, L. M. (1993). Joint estimation of model parameters and outlier effects in time series. J. Amer. Statist. Assoc. 88 284–297.
  • [6] Davidson, J. (1994). Stochastic Limit Theory: An Introduction for Econometricians. Oxford Univ. Press, Oxford.
  • [7] Davis, R. A., Knight, K. and Liu, J. (1992). M-estimation for autoregression with infinite variance. Stochastic Process. Appl. 40 145–180.
  • [8] Davis, R. A. (1996). Gauss–Newton and M-estimation for ARMA processes with infinite variance. Stochastic Process. Appl. 63 75–95.
  • [9] Fox, A. J. (1972). Outliers in time series. J. Roy. Statist. Soc. Ser. B 34 350–363.
  • [10] Genton, M. G. and Lucas, A. (2003). Comprehensive definitions of breakdown-points for independent and dependent observations. J. Roy. Statist. Soc. Ser. B 65 81–94.
  • [11] Hampel, F. R. (1974). The influence curve and its role in robust estimation. J. Amer. Statist. Assoc. 69 383–393.
  • [12] Huber, P. (1964). Robust estimation of a location parameter. Ann. Math. Statist. 53 73–101.
  • [13] Huber, P. (1981). Robust Statistics. Wiley, New York.
  • [14] Künsch, H. (1984). Infinitesimal robustness for autoregressive processes. Ann. Statist. 12 843–863.
  • [15] Mancini, L., Ronchetti, E. and Trojani, F. (2005). Optimal conditionally unbiased bounded-influence inference in dynamic location and scale models. J. Amer. Statist. Assoc. 100628–641.
  • [16] Maronna, R. A., Martin, R. D. and Yohai, V. J. (2006). Robust Statistics: Theory and Methods. Wiley, London.
  • [17] Martin, R. D. and Yohai, V. J. (1986). Influence functionals for time series. Ann. Statist. 14781–818.
  • [18] Martin, R. D. and Yohai, V. (1996). Highly robust estimation of autoregressive integrated time series models. Publicaciones Previas No. 79, Facultad de Ciencias Exactas y Naturales, Univ. Buenos Aires. Available at http://mate.dm.uba.ar/~vyohai/Martin-Yohai-1996.pdf.
  • [19] Martin, R. D., Samarov, A. and Vandaele W. (1983). Robust methods for ARIMA models. In Applied Time Series Analysis of Economic Data (E. Zellner, ed.) 153–177. Washington Bureau of the Census.
  • [20] Masreliez, C. J. (1975). Approximate non-Gaussian filtering with linear state and observation relations. IEEE Trans. Automat. Control 20 107–110.
  • [21] Muler, N., Peña, D. and Yohai, V. J. (2007). Robust estimates for ARMA models. Technical report. Available at http://mate.dm.uba.ar/~vyohai/techrep-muler-pena-yohai.pdf.
  • [22] Peña, D. (1990). Influential observations in time series. J. Bus. Econom. Statist. 8 235–241.
  • [23] Tsay, R. S. (1986). Time series model specification in the presence of outliers. J. Amer. Statist. Assoc. 81 132–141.
  • [24] Yohai, V. J. (1985). High breakdown-point and high efficiency robust estimates for regression. Technical Report # 66, Dept. Statistics, Univ. Washington. Available at http://www.stat.washington.edu/research/reports/1985/tr066.pdf.
  • [25] Yohai, V. J. (1987). High breakdown point and high efficiency estimates for regression. Ann. Statist. 15 642–665.