𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Robust forecasting with exponential and Holt–Winters smoothing

✍ Scribed by Sarah Gelper; Roland Fried; Christophe Croux

Book ID
102215354
Publisher
John Wiley and Sons
Year
2009
Tongue
English
Weight
282 KB
Volume
29
Category
Article
ISSN
0277-6693

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

Robust versions of the exponential and Holt–Winters smoothing method for forecasting are presented. They are suitable for forecasting univariate time series in the presence of outliers. The robust exponential and Holt–Winters smoothing methods are presented as recursive updating schemes that apply the standard technique to pre‐cleaned data. Both the update equation and the selection of the smoothing parameters are robustified. A simulation study compares the robust and classical forecasts. The presented method is found to have good forecast performance for time series with and without outliers, as well as for fat‐tailed time series and under model misspecification. The method is illustrated using real data incorporating trend and seasonal effects. Copyright © 2009 John Wiley & Sons, Ltd.

📜 SIMILAR VOLUMES

Robust exponential smoothing
Robust exponential smoothing
✍ Tomáš Cipra 📂 Article 📅 1992 🏛 John Wiley and Sons 🌐 English ⚖ 602 KB

The paper is devoted to robust modifications of exponential smoothing for time series with outliers or long-tailed distributions. Classical exponential smoothing applied to such time series is sensitive to the presence of outliers or long-tailed distributions and may give inadequate smoothing and fo

Stationary Forecasting; Using Holt-Winte
Stationary Forecasting; Using Holt-Winter and a Modification of Holt-Winter
✍ Dr. Mohammed K. Kazempour 📂 Article 📅 2007 🏛 John Wiley and Sons 🌐 English ⚖ 359 KB

## Abstract The mean square error of the best (projection) linear predictor and some approximation methods are compared. Some analytical results concerning the optimal ‘smoothing constant’ for Holt‐Winter in Moving Average (1), model MA(1), and Autoregressive Moving Average (1,1), model ARMA(1,1),

Long-term sales forecasting using holt–w
Long-term sales forecasting using holt–winters and neural network methods
✍ Apostolos Kotsialos; Markos Papageorgiou; Antonios Poulimenos 📂 Article 📅 2005 🏛 John Wiley and Sons 🌐 English ⚖ 242 KB

## Abstract The problem of medium to long‐term sales forecasting raises a number of requirements that must be suitably addressed in the design of the employed forecasting methods. These include long forecasting horizons (up to 52 periods ahead), a high number of quantities to be forecasted, which l