Seasonality and SARIMAX models

In general, we will work with either quarterly, monthly, or weekly data. This is particularly interesting, because data arising from the same quarter/month/week will exhibit seasonal patterns. For example, if we are working with monthly sales of toys, we will see that they are usually bought in December as gifts. In consequence, all the data points related to December will be correlated. Seasonality terms have associated P/Q terms, which are analogous to their nonseasonal p/q counterparts.

Getting ready

In order to run this recipe, you will need to install the forecast package via install.packages("forecast").

...