[Rd] Re: termplot

[Duncan Murdoch]

On Sat, 24 Jan 2004 13:29:02 +1100, John Maindonald
<john.maindonald at anu.edu.au> wrote:

>Hi Duncan -
>Are you a good person to check with re the inclusion of my fix,
>or some equivalent, for Problem # 6327? 

I'm as good as any.  You can view the bug repository at
<http://bugs.r-project.org/>.  There's an entry there that says Thomas
Lumley has fixed things.   I tried a couple of variations on your bug
example and they seemed to work fine.

>This may be a good time to mention that I'd like to be able to
>add a smooth to the points that appear when partial.resid=TRUE.
>One mechanism would be to allow as argument a panel function that
>can be set to panel.smooth.  (The default might be NULL).
>I'll forward a more detailed suggestion to r-devel.

I think that was added; there's this NEWS file entry:

    o	termplot() has an option to smooth the partial residuals.

You can view the up-to-the minute source at

 http://franz.stat.wisc.edu/cgi-bin/viewcvs.cgi/R/

You need to look in src/library/stats (the new stats package) to find
the termplot source and documentation; it can be annotated to show
what was added on each date.

By default you're seeing the source to r-devel (the upcoming 1.9.0);
you can choose a different branch (e.g. the r 1.8 patches branch) to
see different variations.  I don't think the bug fix for termplot has
been added to the patch branch.  Since the packages were reorganized,
it's a lot harder to add things to both branches, so most things are
only going into r-devel (and new features are never supposed to go
into the patch version, only bug fixes).

Duncan Murdoch