function for re-transforming first differential forecast data

Hi all,

Is there any function for transforming first differential forecast data.
To elaborate, i have done a forecast using ARIMA on data which is first differentiated.
After getting the forecast results, how do I re-transform it back.

You could use the diffinv() function. But you would be much better off letting the ARIMA function do the differencing for you so that the forecast() function will undo the difference as required. For example:

fit <- Arima(WWWusage, order=c(3,1,0))

Here the 1 in the order argument denotes order 1 differencing. This is then reversed in the forecast() function.

Thank you Rob.


This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.