Robust Exponential Smoothing of Multivariate Time Series

23 Pages Posted: 24 Nov 2009

See all articles by Christophe Croux

Christophe Croux

KU Leuven - Faculty of Business and Economics (FEB)

Sarah Gelper

KU Leuven - Faculty of Business and Economics (FEB)

Koen Mahieu

affiliation not provided to SSRN

Date Written: 2009

Abstract

Multivariate time series may contain outliers of different types. In presence of such outliers, applying standard multivariate time series techniques becomes unreliable. A robust version of multivariate exponential smoothing is proposed. The method is affine equivariant, and involves the selection of a smoothing parameter matrix by minimizing a robust loss function. It is shown that the robust method results in much better forecasts than the classic approach in presence of outliers, and performs similar when the data contain no outliers. Moreover, the robust procedure yields an estimator of the smoothing parameter less subject to downward bias. As a byproduct, a cleaned version of the time series is obtained, as is illustrated by means of a real data example.

Keywords: Data cleaning, Exponential smoothing, Forecasting, Multivariate time series, Robustness

Suggested Citation

Croux, Christophe and Gelper, Sarah and Mahieu, Koen, Robust Exponential Smoothing of Multivariate Time Series (2009). Available at SSRN: https://ssrn.com/abstract=1512492 or http://dx.doi.org/10.2139/ssrn.1512492

Christophe Croux (Contact Author)

KU Leuven - Faculty of Business and Economics (FEB) ( email )

Naamsestraat 69
Leuven, B-3000
Belgium

Sarah Gelper

KU Leuven - Faculty of Business and Economics (FEB) ( email )

Naamsestraat 69
Leuven, B-3000
Belgium

Koen Mahieu

affiliation not provided to SSRN ( email )

Register to save articles to
your library

Register

Paper statistics

Downloads
134
Abstract Views
646
rank
212,832
PlumX Metrics