[R] Decomposition of time series with forecast package

[djhurio]

Hi!

I am exploring the forecast package (http://www.robjhyndman.com/
index.php?option=com_content&task=view&id=55&Itemid=71).

I am doing ARIMA modelling with auto.arima() function. Is it possible
to get the decomposition of a time series using the model found by
auto.arima()? I would like to decompose a time series in trend,
seasonal and irregular components according to the model.

I have looked at the decompose() and stl() functions. But these
function do not take into account the specific model found by
auto.arima().


Thanks!
Martins