[R] Complex Time Series

Bernardo Rangel Tura tura at centroin.com.br
Thu Jun 19 00:06:35 CEST 2008


Hi R masters,

In my work I analyse a time serie of number of birth in State of Rio de Janeiro.
After study de ACF e p ACF I conclude the model is:

Non seasonal ar(1)
In 7 days lag 7 days seasonal ma(1)  
In 364 days lag 364 days seasonal ma(1)

If the time serie was Non seasonal ar(1) with one  seasonal ma(1)   is simple
using command arima for fit a time serie, but I don't know HOW TO fit a arima
model in a time serie with 2 diferent seasonal periods

I attach de file ts.csv with the serie.

Thanks in advance....

Bernardo Rangel Tura, M.D, M.P.H, PhD
National Institute of Cardiology
Rio de Janeiro - Brazil



More information about the R-help mailing list