Exponential smoothing based on L-estimation

Přemysl Bejda; Tomáš Cipra

Kybernetika (2015)

  • Volume: 51, Issue: 6, page 973-993
  • ISSN: 0023-5954

Abstract

top
Robust methods similar to exponential smoothing are suggested in this paper. First previous results for exponential smoothing in L 1 are generalized using the regression quantiles, including a generalization to more parameters. Then a method based on the classical sign test is introduced that should deal not only with outliers but also with level shifts, including a detection of change points. Properties of various approaches are investigated by means of a simulation study. A real data example is used as an illustration.

How to cite

top

Bejda, Přemysl, and Cipra, Tomáš. "Exponential smoothing based on L-estimation." Kybernetika 51.6 (2015): 973-993. <http://eudml.org/doc/276221>.

@article{Bejda2015,
abstract = {Robust methods similar to exponential smoothing are suggested in this paper. First previous results for exponential smoothing in $L_1$ are generalized using the regression quantiles, including a generalization to more parameters. Then a method based on the classical sign test is introduced that should deal not only with outliers but also with level shifts, including a detection of change points. Properties of various approaches are investigated by means of a simulation study. A real data example is used as an illustration.},
author = {Bejda, Přemysl, Cipra, Tomáš},
journal = {Kybernetika},
keywords = {change point; exponential smoothing; quantiles; robust methods; sign test},
language = {eng},
number = {6},
pages = {973-993},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Exponential smoothing based on L-estimation},
url = {http://eudml.org/doc/276221},
volume = {51},
year = {2015},
}

TY - JOUR
AU - Bejda, Přemysl
AU - Cipra, Tomáš
TI - Exponential smoothing based on L-estimation
JO - Kybernetika
PY - 2015
PB - Institute of Information Theory and Automation AS CR
VL - 51
IS - 6
SP - 973
EP - 993
AB - Robust methods similar to exponential smoothing are suggested in this paper. First previous results for exponential smoothing in $L_1$ are generalized using the regression quantiles, including a generalization to more parameters. Then a method based on the classical sign test is introduced that should deal not only with outliers but also with level shifts, including a detection of change points. Properties of various approaches are investigated by means of a simulation study. A real data example is used as an illustration.
LA - eng
KW - change point; exponential smoothing; quantiles; robust methods; sign test
UR - http://eudml.org/doc/276221
ER -

References

top
  1. Brown, R. G., Smoothing, Forecasting and Prediction of Descrete Time Series., Prentice-Hall, Englewood Cliffs, NJ 1962. 
  2. Cipra, T., 10.1002/for.3980110106, J. Forecasting 11 (1992), 1, 57-69. DOI10.1002/for.3980110106
  3. Cipra, T., Romera, R., 10.2307/2289888, In: -Statistical Analysis and Related Methods (Y. Dodge ed.), pp. 233-243, 1992. MR1214835DOI10.2307/2289888
  4. Gelper, S., Fried, R., Croux, Ch., 10.2139/ssrn.1089403, J. Forecasting 29 (2010), 3, 285-300. Zbl1203.62164MR2752114DOI10.2139/ssrn.1089403
  5. Hanzák, T., Cipra, T., Exponential smoothing for time series with outliers., Kybernetika 47 (2011), 2, 165-178. Zbl1220.62114MR2828571
  6. Holt, Ch. C., 10.1016/j.ijforecast.2003.09.015, Int. J. Forecasting 20 (2004), 5-10. DOI10.1016/j.ijforecast.2003.09.015
  7. Hyndman, R. J., Koehler, A. B., Ord, J. K., Snyder, R. D., 10.1007/978-3-540-71918-2, Springer, Berlin - Heidelberg 2008. Zbl1211.62165DOI10.1007/978-3-540-71918-2
  8. Jurečková, J., Picek, J., 10.1201/9781420035131, Chapman and Hall/CRC, 2005. Zbl1097.62020DOI10.1201/9781420035131
  9. Koenker, R., Bassett, G., 10.2307/1913643, Econometrica 46 (1978), 1, 33-50. Zbl0482.62023MR0474644DOI10.2307/1913643
  10. Koubková, A., 10.1007/978-3-7908-2656-2, In: COMPSTAT 2004 Proceedings (J. Antoch, ed.), Springer Verlag 2004, pp. 1345-1352. DOI10.1007/978-3-7908-2656-2
  11. Maronna, R. A., Martin, D. R., Yohai, V. J., 10.1002/0470010940, John Wiley and Sons Ltd, Chichester 2006. Zbl1094.62040MR2238141DOI10.1002/0470010940
  12. Moore, G. H., Wallis, W. A., 10.1080/01621459.1943.10501791, J. Amer. Statist. Assoc. 38 (1943), 222, 153-164. Zbl0063.04084MR0008323DOI10.1080/01621459.1943.10501791
  13. Papageorgiou, M., Kotsialos, A., Poulimenos, A., 10.1002/for.943, J. Forecasting 25 (2005), 5, 353-368. MR2190371DOI10.1002/for.943
  14. Romera, R., Cipra, T., 10.1080/03610919508813252, Commun. Statist. - Simulation and Computation 24 (1995), 2, 461-488. Zbl0850.62688MR1333047DOI10.1080/03610919508813252
  15. Wilcoxon, F., 10.2307/3001968, Biometrics Bull. 1 (1945), 6, 80-83. DOI10.2307/3001968
  16. Wolfowitz, J., 10.1214/aoms/1177731281, Ann. Math. Statist. 15 (1944), 2, 163-172. Zbl0063.08310MR0010362DOI10.1214/aoms/1177731281

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.