[R] Packages - a great resource, but hard to find the right one

[hadley wickham]

> This is a strange argument.  A good package will get a good review, which
> may help it to become better.  A review of a weak package can point out how
> it can be fixed.  Reviews will not become stale, just because packages are
> frequently updated by their authors (like some that could be mentioned).
> These are generally smaller changes.  A constructive review will not just be
> concerned with details, but more with the overall aims of the package and
> how they are achieved (or not achieved).

My argument is that package reviews are a rather strange beast, being
a review of something that is neither particularly stable nor remedied
soon after the writing of the review.  Should the review be written
for the package author (perhaps focussing on more technical/internal
details) or for the package-using public (focussing on the overall
philosophy and capabilities)?

This at least seems like something that should be considered when
choosing which packages to review.  The data available from
http://dirk.eddelbuettel.com/cranberries/ (although not currently
arranged in the most useful form for that task) would useful to take
into account.

> Why should JSS, one of the few journals for statistical software, review
> texts?  Task views are a good idea, but are general.  They give only a brief
> and subjective overview (and can hardly be expected to do more).

The problem that started this thread was a problem finding the
relevant R package and I'm not sure how package reviews would help.
You would now have 1,000 lengthy reviews to read through instead of
1,000 brief paragraphs?

That said, package reviews could clearly be useful in their own right,
as peer feedback for authors, and to provide more information for the
general public.

> If you were not an enthusiastic author of many R packages I would start to
> think that you are afraid of being reviewed, Hadley!  What have you against
> someone studying a package, a group of packages or some other aspect of R in
> detail?  Maybe I had better start reviewers on your packages first...

I would be very happy to volunteer my packages for review, and I'd
happily review a package for every package of mine that gets reviewed.
 I have no arguments with the fact that a package review would be a
great learning opportunity for the author, but I'm still not sure what
it gains the wider community (apart from having better software).

Hadley

-- 
http://had.co.nz/