[R] Prediction from Arima model

[Mark Leeds]

Chris: As David mentioned, if you have "new" data, then the interval has to
be a prediction
interval because the difference between a CI and a PI is that the PI is
constructed for data
that hasn't been seen yet. The CI is constructed for data that's already
there. I hope this helps.


On Sat, Aug 31, 2024 at 2:38 PM Christofer Bogaso <
bogaso.christofer using gmail.com> wrote:

> I want to obtain confidence interval for a new data as well as
> estimate of SE for the new data
>
> On Sat, Aug 31, 2024 at 11:58 PM David Winsemius <dwinsemius using comcast.net>
> wrote:
> >
> >
> > Sent from my iPhone
> >
> > > On Aug 31, 2024, at 10:55 AM, Christofer Bogaso <
> bogaso.christofer using gmail.com> wrote:
> > >
> > > Hi,
> > >
> > > I have run following code to obtain one step ahead confidence interval
> > > from am arima model
> > >
> > > library(forecast)
> > >
> > > set.seed(100)
> > >
> > > forecast(Arima(rnorm(100), order = c(1,0,1), xreg = rt(100, 1)), h =
> > > 1, xreg = 10)
> > >
> > > However this appear to provide the Prediction interval, however I
> > > wanted to get the confidence interval for the new value.
> > >
> > > Is there any way to get the confidence interval for the new value?
> >
> > I’m not sure it makes sense to output a confidence interval when you are
> projecting a time series. If you wanted a confidence interval on the past
> data then you can just use standard descriptive methods.
> >
> > —
> > David.
> > >
> > > I also wanted to get the estimate of SE for the new value which is
> > > used to obtain the confidence interval of the new value. Is there any
> > > method available to obtain that?
> > >
> > > ______________________________________________
> > > R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > > https://stat.ethz.ch/mailman/listinfo/r-help
> > > PLEASE do read the posting guide
> https://www.R-project.org/posting-guide.html
> > > and provide commented, minimal, self-contained, reproducible code.
> >
>
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> https://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

	[[alternative HTML version deleted]]