[R] User error (was arima.sim bug?)

[Brian D Ripley]

On Tue, 4 Oct 2005, Rolf Turner wrote:

>
> Brian Ripley wrote (in response to S. E. Kemp):
>
> > > I am using the arima.sim function to generate some AR time series.
> > > However, the function does not seem to produce exactly the same time
> > > series when I specify the innov parameter. For example
> 	<snip>
> > > Given the fact that I have provided the innovations shouldn't the time
> > > series be exactly the same?
> >
> > No.  Hint: where does the randomness for the burn-in come from?
>
> 	What then, pray tell, is the point of having the
> 	``innov'' argument at all?

To allow non-Gaussian innovations, in particular for use in bootstrapping
time series.  (This started life in package boot and is used in
example(tsboot).)

-- 
Brian D. Ripley,                  ripley at 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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595