Share This

“A variation of the time series ARIMA method where the lags for auto-regression (AR) and moving average (MA) are defined in terms of multiples of the seasonality. For example, monthly data has a seasonality of 12, so the AR term (P) would be 1 or 2 to indicate 12 or 24 months. Similarly, differencing to resolve the trend occurs at the seasonal level, so a difference of 1 is accomplished by subtracting values that are 12 months apart.”

« Back to Glossary Index Download Tooltip Pro
By |February 1st, 2019|Comments Off on seasonal ARIMA (SARIMA) [SARIMA]