Abstract
This chapter presents a robustness analysis of the forecasting statistics introduced in the previous chapter under the following distortion types: four functional distortion varieties of the regression function, additive outliers, and correlation between random errors. A quantitative characterization of forecasting robustness is obtained by using the robustness indicators introduced in Chap. 4, namely the forecast risk instability coefficient and the δ-admissible distortion level. Robust forecasting statistics are constructed by using Huber estimators and a specially chosen type of M-estimators for the regression function parameters. A local-median forecasting algorithm is proposed to mitigate the influence of outliers under regression models, and its robustness is evaluated.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Atkinson, A., Riani, M.: Robust Diagnostic Regression Analysis. Springer, New York (2000)
Borovkov, A.: Mathematical Statistics. Gordon & Breach, Amsterdam (1998)
Borovkov, A.: Probability Theory. Gordon & Breach, Amsterdam (1998)
Brockwell, P., Davis, R.: Introduction to Time Series and Forecasting. Springer, New York (2002)
Bulinsky, A., Shyryaev, A.: Theory of Random Processes (in Russian). Fizmatlit, Moscow (2003)
Chatfield, C.: Time Series Forecasting. Chapman & Hall/CRC, Boca Raton (2001)
Croux, C., Filzmoser, P.: Discussion of “A survey of robust statistics” by S. Morgenthaler. Stat. Meth. Appl. 15(3), 271–293 (2007)
Davison, A.: Statistical Models. Cambridge University Press, Cambridge (2009)
Draper, N., Smith, H.: Applied Regression Analysis. Wiley, New York (1998)
Green, P.: Penalized likelihood for general semi-parametric regression models. Int. Stat. Rev. 55, 245–249 (1987)
Hampel, F., Ronchetti, E., Rousseeuw, P., Stahel, W.: Robust Statistics: The Approach Based on Influence Functions. Wiley, New York (1986)
Hettmansperger, T.: A practical affine equivariant multivariate median. Biometrika 89(4), 851–860 (2002)
Huber, P.: Robust Statistics. Wiley, New York (1981)
Kharin, Y.: Robustness in Statistical Pattern Recognition. Kluwer, Dordrecht (1996)
Kharin, Y.: Robustness of signal prediction under distortions. In: Signal Analysis and Prediction. Proceedings of the I European Conference on Signal Analysis and Prediction, vol. 1, pp. 219–221. ICT Press, Prague (1997)
Kharin, Y.: Robust forecasting of parametric trends. Stud. Classif. Data Anal. 17, 197–206 (2000)
Kharin, Y.: Robustness analysis in forecasting of time series. In: Dutter, R., Filzmoser, P., Gather, U., Rousseeuw, P. (eds.) Developments in Robust Statistics, pp. 180–193. Springer, Heidelberg (2003)
Kharin, Y.: Sensitivity analysis of risk of forecasting under multivariate linear regression model with functional distortions. In: Computer Data Analysis and Modeling, vol. 2, pp. 50–55. BSU, Minsk (2004)
Kharin, Y.: Optimality and Robustness in Statistical Forecasting (in Russian). BSU, Minsk (2008)
Kharin, Y.: Optimality and robustness in statistical forecasting. In: Lovric, M. (ed.) International Encyclopedia of Statistical Science, vol. 1, pp. 1034–1037. Springer, New York (2011)
Kharin, Y.: Robustness of the mean square risk in forecasting of regression time series. Comm. Stat. Theor. Meth. 40(16), 2893–2906 (2011)
Kharin, Y., Maevskiy, V.: Robust regression forecasting under functional distortions. Autom. Rem. cont. (11), 125–136 (2002)
Launer, R., Wilkinson, G.: Robustness in Statistics: Proceedings of a Workshop. Academic, New York (1979)
Makridakis, S., Hyndman, R., Wheelwright, S.: Forecasting: Methods and Applications. Wiley, New York (1998)
Marcus, M., Minc, H.: A Survey of Matrix Theory and Matrix Inequalities. Allyn and Bacon, Boston (1964)
Oja, H.: Descriptive statistics for multivariate distributions. Stat. Probab. Lett. 1, 327–332 (1983)
Pena, D., Tiao, G., Tsay, R.: A Course in Time Series Analysis. Wiley, New York (2001)
Rieder, H.: Robust Asymptotic Statistics. Springer, New York (1994)
Rousseeuw, P., Leroy, A.: Robust Regression and Outlier Detection. Chapman & Hall, London (1987)
Seber, G., Lee, A.: Linear Regression Analysis. Wiley-Interscience, Hoboken (2003)
Small, C.: A survey of multidimensional medians. Int. Stat. Rev. 58, 263–277 (1990)
Tayler, D.: A distribution-free M-estimator of multivariate scatter. Ann. Stat. 15, 234–251 (1987)
Varmuza, K., Filzmoser, P.: Introduction to Multivariate Statistical Analysis in Chemometrics. Taylor & Francis—CRC Press, Boca Raton (2009)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Kharin, Y. (2013). Robustness of Time Series Forecasting Based on Regression Models. In: Robustness in Statistical Forecasting. Springer, Cham. https://doi.org/10.1007/978-3-319-00840-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-00840-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-00839-4
Online ISBN: 978-3-319-00840-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)