ABSTRACT
In this chapter, the authors start with a discussion of time series components, then move to the idea of decomposing time series into distinct components and applying simple forecasting methods, including Naive, Global Average, Simple Moving Average, and Simple Exponential Smoothing. The seasonal pattern will introduce some similarities from one period to another. One of the classical textbook methods for decomposing the time series into unobservable components is “Classical Seasonal Decomposition”. There are other techniques that decompose series into error, trend, and seasonal components but make different assumptions about each component. Finally, in the case of seasonal data, there is a simple forecasting method that can be considered as a good benchmark in many situations. One of the most powerful and efficient forecasting methods for level time series is Simple Exponential Smoothing. Finally, there is an alternative form of SES, known as error correction form, which can be obtained after some simple permutations.
