You won't be able to do it with arima or arima0. This is not a sensible
way to fit such a model, which is just 365 uncoupled time series.
Just do a OLS regression on year-lagged values, or write some code to
combine the likelihoods from the 365 series and maximize the combined
likelihood.
On Mon, 22 Mar 2004, michele lux wrote:
> hallo to all
> I've to calculate an arima model and I need only the
> first and 365 th parameter and also the sar1 and the
> intercept, so I'm traing with:
>
arima(X,order=c(365,0,0),seasonal=list(order=c(1,0,0),..),fixed=c(NA,rep(0,363),NA,NA,NA),transform.pars=F)
>
> but the error answer is:
> Error in polyroot(z) : polynomial degree too high (49
> max)
>
> also there are problems in allocating memory (I've 512
> mb ram)
> may be somebody could help me?
> can R do it?
> thanks
> michele
>
> ______________________________________________________________________
>
> http://it.yahoo.com/mail_it/foot/?http://it.mail.yahoo.com/
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
>
>
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595