arima.sim (PR#2256)

ripley@stats.ox.ac.uk ripley@stats.ox.ac.uk
Tue, 5 Nov 2002 13:21:39 +0000 (GMT)


S-PLUS has an unusual parametrization.

See ?arima for that used by R.

Working as documented is not a bug in R!

On Mon, 4 Nov 2002 pchoquet@mat.ulaval.ca wrote:

> Hi,
>
> when just simulating MA(1) series with
>
> arima.sim(100, model=list( ma=0.8 ))
>
> (in the ts package), I get sample ACF and  PACF like I had theta_1 < 0
>
>
> for example, with acf(series[,i], 20, "correlation") or "partial",
> I get : (see acf_R.emf)
>
> and those should look like : (see ma1.JPG)
>
> but they look more like : (see ma1wr.JPG)
>
> This is not an exception and S-PLUS did not appear to do that.
> And when I enter a theta_1 < 0, it gives results like I entered a theta_1 >
> 0.
>
> I have R v1.5.1 ,S-PLUS v6.1

-- 
Brian D. Ripley,                  ripley@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._