Hi,
I m working on time series forecasting.I was checking ARIMA and
GARCH model for forecasting.Is there any possibility that we can include
test data as input for predict function.I am working on real time
forecasting where i would be getting real time feeds using which i need
forecas
,
Raghav
On Fri, Mar 26, 2010 at 2:24 PM, Prof Brian Ripley wrote:
> Just save() the model fit. See ?save.
>
>
> On Fri, 26 Mar 2010, RAGHAVENDRA PRASAD wrote:
>
> Hi,
>>
>> Thanks for the info.I will try this.But i am working on real time
>> analytics
>>
; there's probably a far more sophisticated way to do this, but if I'm
> understanding you correctly this is a quick fix...
>
> regards
> katya
>
>
> >>> RAGHAVENDRA PRASAD 2010/03/26 09:53 AM >>>
>
> Hi,
>
> I have a NN model build using AM
Hi,
I have a NN model build using AMORE and NNET.If i want to reuse the model
built on later date.How can i store this model.In what format should i need
to store the model.I wont be saving the session.I want to just store the
model and recall this model whenever required.Is it possible to store?
Hi,
Although my doubt is pretty,as i m not from stats background i am not sure
how to proceed on this.
Currently i am doing a forecasting.I used ARIMA to forecast and time series
was volatile i used garchFit for residuals.
How to use the output of Garch to correct the forecasted values from ARIMA
5 matches
Mail list logo