R programming has several tools that can be used when dealing with events in a time series. We can look at the time series from several aspects, evaluate the components involved in the data, construct a model of the time series behavior, and estimate or forecast time series events going forward.
This chapter covers the analysis of time series data with the objective of forecasting. There are several areas in R programming that can be used for time series forecasting:
Converting your data into an R-formatted time series
Examining seasonality effects
Simple smoothing
Basic trend analysis, including decomposing your time series into seasonal, trend, and irregular components
Exponential smoothing, including Holt-Winters filtering, correlogram, and box test
ARIMA modeling