Hi,
i want to predict a seasonal time series (number of time series value =
240), (period of season =24),
i use zelig function , but i don't know the right use of argument and the
prediction that I obtain isn't right.
For example:
z.out1<- zelig(Diff(Y,d,ds,per) ~ lag.eps(q,qs) + lag.y(p,ps), data =
mydata, model = "arima")
arguments:
Diff:
Y<- a column of my data
d<-?
ds<-?
per <- 24
lag.eps:
q<-?
qs<-?
lag.y:
p<- ?
ps<-?
Can anybody help me?
P.S
i've found this tutorial but i can't understand so much:
In addition to independent variables, zelig() accepts the following
arguments to specify the ARIMA model:
. Diff(Y, d, ds, per) for a dependent variable Y sets the number
of non-seasonal differences (d), the
number of seasonal differences (ds), and the period of the season (per).
. lag.y(p, ps) sets the number of lagged observations of the
dependent variable for non-seasonal (p) and
seasonal (ps) components.
. lag.eps(q, qs) sets the number of lagged innovations, or
differences between the observed value of the
time series and the expected value of the time series for non-seasonal (q)
and seasonal (qs) components.
Thanks
Riccardo
Show replies by date