[R] a question about arimax, please

[peter dalgaard]

In package TSA?

You may need to do some studying for yourself, this is complicated stuff. 

As I read the help page, the intention is that the transfer= bit is to allow a _covariate_ to affect the process in an ARMA-like fashion. So c(1,0) would be AR(1)-like which if I remember correctly corresponds to an exponentially decaying effect of instantaneous shocks to the system. And c(0,0) would be MA(0)-like, which I suppose would be an effect that only affected the same period as the instantaneous shock. In the example, we have the same covariate (Sept. 2001) contributing with both kinds of effect, so xtransf= has the same variable twice.

-pd

On 06 Oct 2014, at 19:11 , Erin Hodgess <erinm.hodgess at gmail.com> wrote:

> Hello!
> I have about the arimax function, please:
> If you see the example page, you see the following:
> # Exhibit 11.6
> air.m1=arimax(log(airmiles),order=c(0,1,1),seasonal=list(order=c(0,1,1),
> period=12),xtransf=data.frame(I911=1*(seq(airmiles)==69),
> I911=1*(seq(airmiles)==69)),
> transfer=list(c(0,0),c(1,0)),xreg=data.frame(Dec96=1*(seq(airmiles)==12),
> Jan97=1*(seq(airmiles)==13),Dec02=1*(seq(airmiles)==84)),method='ML')
> Now the part that I am puzzled about the "transfer" argument, please. It is
> supposed to be the MA order and the AR order, respectively. However, the AR
> order is 0. Should that be reversed, please?
> Thanks,
> Erin.
> 
> -- 
> Erin Hodgess
> Associate Professor
> Department of Mathematical and Statistics
> University of Houston - Downtown
> mailto: erinm.hodgess at gmail.com
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> 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.

-- 
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com