On Mon, 19 Nov 2001, Hiroyuki Kawakatsu wrote:
> At Mon, 19 Nov 2001 08:36:38, you wrote:
>
> > I get the labels I expect: if this is quarterly data the lags are
labelled
> > in years. That is what `frequency = 4' is intended to mean: 4
> > observations per unit of time.
>
> some further thoughts convinces me that this is a mis-feature. if you
> ask any person what is the lag i autocorrelation, the answer would be
> corr(y_t, y_{t-i}). so you would expect the lag labels to be based on
> observation lags, not years. if you still think the current feature is
> the correct implementation, i suggest that you make this clear in the
> help to avoid future annoying mails from the annoyed like me:
>
> lag.max: maximum lag at which to calculate the acf. Default is
> 10*log10(N) where N is the number of observations.
>
> *Note that the lag labels in the plots are based on unit of
> time, not observation lags.*
I do think it is correct, and furthermore no one else has thought otherwise
in 2.5 years of it being in R. It's the same interpretation as S, snd that
doesn't have such a comment either.
You will find *all* time-series plots are labelled in units of time,
not observation lags. It says `Lag', not `lags', and that's a
crucial
difference.
See the section in the FAQ on `what is a bug?'.
--
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._