Abstract
The robust estimation of the autoregressive parameters is formulated in terms of the quadratic programming problem. This article follows a proposal of Mallows, using simultaneously two weight functions. New robust estimates are yielded, by combining optimally the Huber-type “ residual” weight function with a “ position ” weight function. The behavior of the estimators is studied numerically, under the additive and innovation outlier generating model. Monte Carlo results show that the proposed estimators compared favorably with respect to M-estimators and Bounded Influence estimators(GM-estimators). Based on these results we conclude that one can improve the robust properties of Ar(p) estimators using the proposed optimization technique.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. E. P. Box and G. M. Jenkins. In Time Series Analysis Forecasting and Control. Holden-Day, San Francisco, 1976.
I. Barrodale and D.K. Roberts. Applications of mathematical programming to lp-approximation. In Nonlinear Programming, J. B. Rosen, O. L. Mangasarian and K. Ritter, eds., Academic Press, New York, 1970.
I. Barrodale and D. K. Roberts. An improved algorithm for discrete II linear approximation. In SIAM J. Numer. Anal., 10, 889–848, 1973.
O. H. Bustos and V. J. Yohai. Robust estimates for arma models. In Journal of the American Statistical Association, 81, 155–168, 1986.
P. J. de Jongh and T. de Wet. Trimmed mean and bounded influence estimators for the parameters of the ar(1) process. In Commun.Statist.-Theor. Meth., 14, 1861–1875, 1985.
L. Denby and R. D. Martin. Robust estimation of the first-order autoregressive parameter. In Journal of the American Statistical Association, 74, 140–146, 1979.
R.J. Carroll D. M. Giltinan and D. Ruppert. Some new estimation methods for weighted regression when there are possible outliers. In Technometrics, 28, 219–230, 1986.
F. Schweppe E. Handschin, I. Kohlas and A. Fiechter. Bad data analysis for power system state estimation. In IEEE Transactions on Power Apparatus and Systems, 2, 829–887, 1975.
F. R. Hampel. Optimally bounding the gross-error-sensitivity and the influence of position in factor space. In 1978 Proceedings of the ASA, Statistical Computing Section, 59–64, 1978.
P.J. Huber. Robust regression: Asymptotics, conjectures, and monte carlo. In Annals of Statistics, 1, 799–821, 1973.
P. J. Huber. In Robust Statistics. John Wiley, New York, 1981.
P. J. Huber. Minimax aspects of bounded-influence regression. In Journal of the American Statistical Association, 78, 66–72, 1983.
W. S. Krasker and R. E. Welsch. Efficient bounded-influence regression estimation. In Journal of the American Statistical Association, 77, 595–604, 1982.
R. J. Carroll L. A. Stefanski and D. Ruppert. Optimally bounded score functions for generalized linear models with applications to logistic regression. In Biometrica, 73, 2, 413–24, 1986.
C. H. Lee and R. Martin. M-estimates for arma process. In Technical Report 23, University of Washington, Dept. of Statistics, 1982.
C. L. Mallows. Influence functions. In National Bureau of Economic Reasearch Conference on Robust Regression in Cambridge, Massachusetts, 1973.
C. L. Mallows. On some topics in robustness. In unpublished memorandum, Bell Telephone Laboratories, Murray Hill, New Jersey, 1975.
A. Marazzi. In Robust Linear Regression Programs in RO-BETH, Reasearch Report No. 24. Eidgenoessische Technishe Hochschule, Zuerich, Fachgruppe fuer Statistik, 1980.
R. D. Martin. Robust of autoregressive models. In Directions in Time Series. eds. D. R. Brillinger and G. C. Tiao, Haywood, CA: Institute of Mathematical Statistics, 1980.
R.E. Welsch. Regression sensitivity analysis and bounded-influence estimation. In Evaluation of Econometric Models, J. Kmenta and J. B. Ramsey, eds. Academic Press, New York, 1980.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag New York, Inc.
About this paper
Cite this paper
Camarinopoulos, L., Zioutas, G., Bora-Senta, E. (1996). An Optimisation Technique For Robust Autoregressive Estimates. In: Robinson, P.M., Rosenblatt, M. (eds) Athens Conference on Applied Probability and Time Series Analysis. Lecture Notes in Statistics, vol 115. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-2412-9_8
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2412-9_8
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-94787-7
Online ISBN: 978-1-4612-2412-9
eBook Packages: Springer Book Archive