[R] arima function

Prof Brian Ripley ripley at stats.ox.ac.uk
Wed Feb 4 12:05:18 CET 2004


You can look the message up!  ?optim gives

convergence: An integer code. '0' indicates successful convergence.
          Error codes are

          '1' indicates that the iteration limit 'maxit' had been
               reached.

and so you should try an increased limit via the optim.control argument.

If I understand correctly, you have two possible ways to model trends, and 
it is likely that makes the optimization ill-determined.

On Wed, 4 Feb 2004, Gaelle BARROT wrote:

> Hello,
> I am a beginner user of R and I would like to estimate a model with AR
> errors. I use arima function:
> 
> modele
> <-arima(conso,xreg=var.exogenes,order=c(ordre,0,0),include.mean=TRUE,method
> ="CSS")
> 
> My inputs are dummies for each month except one, and the same thing for
> each day and each hour.   I have this error message:
> Warning message:
> possible convergence problem: optim gave code= 1 in: arima(as.ts(conso),
> xreg = table, order = c(10, 0, 0), include.mean = TRUE,
> 
> I try to estimate this model with SAS and I have a result.

> Have you a solution to solve this problem?

-- 
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




More information about the R-help mailing list