R help - Apr 2012 - Manually reconstructing arima model from coefficients

Colleagues

I am a new to R but already love it.

I have the following problem:
I fitted arima model to my time series like this (please ignore modeling
parameters as they are not important now):
x = scan("C:/data.txt") 
x = ts(x, start=1, frequency=1)
x.fit<-arima(x, order = c(1,0,0), seasonal = list(order=c(0,0,1)))
 
Now I want to use this model for forecasting and backtesting (!). My goal is
to apply exactly this model to different data ? another time series object,
let?s call it ?y?. How can I do this in R.

One of the options is to extract coefficients and to create my own function
that can be applied to any time series but I suspect and hope that there is
a better way of doing this.
If there is not an easy option can anyone suggest a complete equation that
includes seasonal terms  that can be easily programmed (for example in C)
for a person who knows some programming but very little math.

Thank you. 


--
View this message in context:
http://r.789695.n4.nabble.com/Manually-reconstructing-arima-model-from-coefficients-tp4566082p4566082.html
Sent from the R help mailing list archive at Nabble.com.

What exactly do you mean by "apply" it to a different data set?
Unlike regular regressions, time series models don't (generally) use
new data to make forecasts ...

By the way, this is a good guide to the time series functionality
available in R: http://cran.r-project.org/web/views/TimeSeries.html

Michael

On Tue, Apr 17, 2012 at 5:54 PM, sergey777 <ssamson at uwo.ca>
wrote:
> Colleagues
>
> I am a new to R but already love it.
>
> I have the following problem:
> I fitted arima model to my time series like this (please ignore modeling
> parameters as they are not important now):
> x = scan("C:/data.txt")
> x = ts(x, start=1, frequency=1)
> x.fit<-arima(x, order = c(1,0,0), seasonal = list(order=c(0,0,1)))
>
> Now I want to use this model for forecasting and backtesting (!). My goal
is
> to apply exactly this model to different data ? another time series object,
> let?s call it ?y?. How can I do this in R.
>
> One of the options is to extract coefficients and to create my own function
> that can be applied to any time series but I suspect and hope that there is
> a better way of doing this.
> If there is not an easy option can anyone suggest a complete equation that
> includes seasonal terms ?that can be easily programmed (for example in C)
> for a person who knows some programming but very little math.
>
> Thank you.
>
>
> --
> View this message in context:
http://r.789695.n4.nabble.com/Manually-reconstructing-arima-model-from-coefficients-tp4566082p4566082.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

Michael

My final goal is to perform forecasting in real time. My historical data that is
used for training consist of about 2000 samples. Fitting ARIMA model
x.fit<-arima(x, order = c(5,0,0), seasonal = list(order=c(0,0,1))) takes
about 3-5 minutes, often I do not have so much time between receiving new
samples of data. Therefore, I want to re-create my arima model let's say
only every 50 samples but I want to update my forecast every time new data
sample arrives (in a real time).

In other words I want to apply my arima model to forecasting future events that
will occurre not right after the model was created but some time later after a
few more intermediate samples were received. I think this problem is similar to
applying already fitted arima forecasting to a new time series object that has
similar statistical properties as a tested set, since these are the same series
just shifted in the future.

	[[alternative HTML version deleted]]