R devel - Mar 2002 - monthplot() in R?

The monthplot function in S is useful for plotting seasonal data.
It's not in base R or the ts package; is it in one of the contributed
packages?  (I've written a quick version for myself; if there isn't
one generally available already, I'll make it public somehow.)

Duncan Murdoch
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

>>>>> "Duncan" == Duncan Murdoch
<dmurdoch@pair.com> writes:
    Duncan> The monthplot function in S is useful for plotting
    Duncan> seasonal data.  It's not in base R or the ts
    Duncan> package; is it in one of the contributed packages?
    Duncan> (I've written a quick version for myself; if there
    Duncan> isn't one generally available already, I'll make it
    Duncan> public somehow.)

yes; I've found this a missing feature occasionally myself.
If I remember properly, S' version built on the output of sabl()
whereas we'd need one building on stl() out --- if any at all.
As a matter of fact, I'd like a more general setup that does not
only work with periodicity 12.
monthplot() would then only be a compatibility wrapper calling
the more general function.

Note that Brian Ripley has recently added quite a few things to
`ts' in R-devel, including StructTS() for structured time-series
analysis which includes seasonality.

Martin Maechler <maechler@stat.math.ethz.ch>
http://stat.ethz.ch/~maechler/
Seminar fuer Statistik, ETH-Zentrum  LEO C16	Leonhardstr. 27
ETH (Federal Inst. Technology)	8092 Zurich	SWITZERLAND
phone: x-41-1-632-3408		fax: ...-1228			<><
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

I wrote up monthplot, and Brian Ripley put it in r-devel (to be 1.5.0
at the end of next month).

The default method takes 3 inputs:  x, time, and phase.  x is the time
series, time is the time corresponding to each observation (not
necessarily evenly spaced), and phase is a variable that categorizes
the observations, e.g. the month.  It produces a separate small time
series plot for each value of phase.  The ts, stl, and StructTS
methods automatically fill in the time and phase values from the time
series attributes.

Duncan Murdoch
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._