g13agf
g13agf
© Numerical Algorithms Group, 2002.
Purpose
G13AGF Univariate time series, update state set for forecasting
Synopsis
[st,anexr,ifail] = g13agf(st,mr,par,c,anx<,ifail>)
Description
The time series model is specified as outlined in G13AFF. This
also describes how the state set, which contains the minimum
amount of time series information needed to construct forecasts,
is made up of
(i) the differenced series w (uncorrected for the constant c),
t
for (N-P*s)<t<=N,
(ii) the d' values required to reconstitute the original series
x from the differenced series w ,
t t
(iii) the intermediate series e , for (N-max(p,Q*s))<t<=N,
t
(iv) the residual series a , for (N-q)<t<=N.
t
If the number of original undifferenced observations was n, then
d'=d+(D*s) and N=n-d'.
To update the state set, given a number of new undifferenced
observations x , t=n+1,n+2,...,n+k, the four series above are
t
first reconstituted.
Differencing and residual calculation operations are then applied
to the new observations and k new values of w ,e and a are
t t t
derived.
The first k values in these three series are then discarded and a
new state set is obtained.
The residuals in the a series corresponding to the k new
t
observations are preserved in an output array. The parameters of
the time series model are not changed in this routine.
Parameters
g13agf
Required Input Arguments:
st (:) real
mr (7) integer
par (:) real
c real
anx (:) real
Optional Input Arguments: <Default>
ifail integer -1
Output Arguments:
st (:) real
anexr (:) real
ifail integer