What kind of problem? For one variable or more?
What have you tried? For only a single time series, the standard
approach that I learned from Box and Jenkins, Time Series Analysis,
Forecasting and Control, starts by preparing both acf and pacf, both of
which are functions in R. If the acf shows only 1, 2 or 3 significant
spikes, it suggests a moving average only model of the indicated order.
If the pacf shows only 1, 2, or 3 significant spikes, that suggests an
autogregression only model. If the acf shows very high autoregressions
of all orders with very slow decay, it suggests at least one difference.
If both acf and pacf show reasonable, possibly oscillating decay with
no clear cut-off, then I'd first try an ARMA(1,1), then look at the
residuals and expand the model as needed.
Finally, have you read the posting guide!
http://www.R-project.org/posting-guide.html? This suggests, among other
things, that you provide a toy example that a potential respondant could
easily copy from your email, test a few modifications, and prase a reply
in a minute or so. This also helps clarify your question so any
respondants are more likely to suggest something that is actually useful
to you. Moreover, many people have reported that they were able to
answer their own question in the course of preparing a question for this
list using the posting guide.
hope this helps.
spencer graves
Amir Safari wrote:
>
>
> Dear All ,
> Is it possible to find and select the best lags for time series in R? (
Lag Selection Problem )
> Could you please introduce a package or function for this ?
> Thanks a lot
>
>
> __________________________________________________
>
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html