Re: [Gretl-users] Classical Decomposition
Am 01.02.2008 11:50, Tom La Bone schrieb:
Classical decomposition is breaking a univariate times series down
into a
trend component, a seasonal component, and a random noise component (for
example, see Chapter 1 of Brockwell and Davis intro to time series book).
Tom
For a reasonable (IMHO) definition of trend component that is only
possible if you replace "random noise component" by "stationary
component".
So I am still not entirely sure, but I suspect you may want to do
Box-Jenkins ARIMA modeling. (Model->Time Series->Arima)
HTH,
sven