Correlation analysis of time series data is one of the main steps of the analysis process. Throughout this chapter, we introduced different approaches for identifying the correlation between a series and its lags and causality between two time series. Those approaches include the use of both statistical methods, such as the ACF and PACF, and data visualization methods. The application of the correlation analysis plays a pivotal role in many time series applications, from the descriptive analysis of a series, as we saw in this chapter, to tuning time series forecasting models, such as the ARIMA model.
In the next chapter, we will introduce strategies for training, testing, benchmarking, and evaluating forecasting models.
