Box-Jenkins autoregressive integrated moving average

The Box-Jenkins autoregressive integrated moving average (ARIMA) is a statistical method used for time series analysis and forecasting. It assumes that future values of a time series are related to past values and past errors.1

ARIMA models are applicable to stationary time series, meaning those with a constant mean, variance, and autocorrelation function. For non-stationary series, differences between successive values can be taken to create a stationary series to which the ARIMA model can be applied.1

Moving averages, a related concept, are calculations of successive prices averaged over a period to smooth out price movements and gauge market trends. Different time periods for moving averages can indicate short-term or long-term trends.2