\( \newcommand{\mathbbm}[1]{\boldsymbol{\mathbf{#1}}} \)

Chapter 4 Introduction to ETS

Now that we know how time series can be decomposed into components, we can discuss the ETS model and its connection with Exponential Smoothing methods, focusing on the most popular of those. We do not discuss in detail how the methods were originally derived and how to work with them. Instead, we focus on the main ideas behind the conventional ETS, as formulated by Hyndman et al. (2008), and the connection between Exponential Smoothing and ETS.

The reader interested in the history of Exponential Smoothing, how it was developed, and what papers contributed to the field can refer to the reviews of Gardner (1985) and Gardner (2006). They summarise all the progress in Exponential Smoothing up until 1985 and until 2006, respectively.


• Gardner, E.S., 2006. Exponential Smoothing: The State of the Art-Part II. International Journal of Forecasting. 22, 637–666. https://doi.org/10.1016/j.ijforecast.2006.03.005
• Gardner, E.S., 1985. Exponential Smoothing: The State of the Art. Journal of Forecasting. 4, 1–28. https://doi.org/10.1002/for.3980040103
• Hyndman, R.J., Koehler, A.B., Ord, J.K., Snyder, R.D., 2008. Forecasting with Exponential Smoothing: The State Space Approach. Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-71918-2