Box–Jenkins method: Difference between revisions

Revision as of 11:28, 18 May 2015

Revision as of 03:25, 19 May 2015

Line 14:

===Stationarity and seasonality===

The first step in developing a Box–Jenkins model is to determine if the [[time series]] is [[Stationary process|stationary]]. andIf if thereit is anynot significantstationary [[seasonality]]the thatdata needsset tomust be modelleddifferenced to attain stationarity.

====Detecting stationarity====

Stationarity can be assessed from a [[run sequence plot]]. The run sequence plot should show constant ___location and [[Scale (ratio)|scale]]. It can also be detected from an [[autocorrelation plot]]. Specifically, non-stationaritystationary data is often indicated by anpatterns of decay in the autocorrelation plot. withThe veryPartial slowautocorrelation decayfunction should also be viewed, together the shapes and spikes of the ACF and PACF will indicate what type of [[Autoregressive integrated moving average]] will best predict future forecasts.

====Detecting seasonality====