[R] [gently off topic] arima seasonal question

Prof Brian Ripley ripley at stats.ox.ac.uk
Fri Jul 2 06:57:00 CEST 2004


arima() fits a seasonal ARIMA model.  I have no idea what `seasons' you 
have in mind, but they can be used for weekly effects in daily data, for 
example, and might also be appropriate for a yearly effect in weekly data 
(provided you have the same number of weeks each year and are not subject 
to the vagarities of holidays -- e.g. weekly abundance measures of 
animals).

This is answered in all good books on time series, including some of those 
referred to in ?arima.

On Thu, 1 Jul 2004, Laura Holt wrote:

> When using the arima function with the seasonal option, are the seasonal 
> options only good for monthly and quarterly data, please?
> 
> Also, I believe that weekly and daily data are not appropriate for seasonal 
> parm estimation via arima.
> 
> Is that correct, please?

-- 
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