Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Re: Empirical Bayes using meta ado


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Re: Empirical Bayes using meta ado
Date   Fri, 26 Jul 2002 12:15:01 +0100

Roger Harbord wrote about -meta- (STB-38/STB-42/STB-43):

< snip >
>
> I'd agree that this is a little confusing and arguably the -ebayes-
> option should do this for you automatically.  However, this
> two-stage
> procedure does make it clearer how the estimates are being
> produced, and
> the -ebayes- option seems unlikely to be of interest to
> casual users.
>
> Picking up on another current thread (Hodrick
> Prescott-Filter / outdated
> modules - posts by Kit Baum and Nick Cox in particular),  this is
> another program from the STB archive.  So as Kit wrote,
> "... the program
> itself can't be altered, only updated by a later published
> version." But
> maybe in this case an extra sentence could usefully be added to the
> help file?? I'm less clear if this is possible. As I
> understand Kit's
> post, updates to STB/SJ material need to be published in
> the SJ. This
> hardly seems worthwhile for adding one sentence to a help file.

The Stata Journal is more than willing to carry notices
of updates to programs and/or help files previously published in the
Stata
Technical Bulletin (and, naturally, the Journal itself).

Those with access to the Journal can see an example
at Stata Journal 2(2), 226 (2002). For those who
can see the contents page at

http://www.stata-journal.com/sj2-2.html

the heading is "Software updates".

The write-up can be as brief as seems appropriate.

"The help file has been revised to clarify what is
done by the -ebayes- (empirical Bayes) option."

would, in my view, be perfectly acceptable as
the body of an update note if that was just what the authors wanted
to say.

Lest this seem trivial, let me emphasise
the more important side-effects:

1. Even this formal micropublication (nanopublication?)
will be indexed in the stata*.key files. Therefore,
provided that you keep up-to-date with -update-,
-search- will find the relevant publications.

Thus suppose someone directs you to Patrick
Royston's -stpm- published in SJ 1(1). If
you

search stpm

you will see not only the original reference,
but also one to a note showing that bugs have been
found and fixed which was published in SJ 2(2).

2. By the same token, the updated software
can be downloaded easily with -net-.

The example given is of a correction
to software accompanying an article
first published in the SJ, but
as stressed, we will carry notes
of corrections and updates to STB-published
software. And we will, most of the time, be able
to fit such a note in the next issue.

Nick
n.j.cox@durham.ac.uk
Executive Editor, Stata Journal

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index