Dear all,
Almost all analyses I have done in Stata are used for publication of
papers. These analyses usually include the use of several packages, some
of them new, or still little (very specific programs) used by most Stata
users.
In this respect, I would like to discuss two issues, which I think that
are extremely important to those using Stata for research.
First, most packages (at least those I have used) fail to provide
references and detail on how their estimates are obtained (formulae).
For instance, the program -genhwcci- estimates a standard error for a
estimate called disequilibrium coefficient (D), but no reference is given
to show to the users where the formulae come from.
Second, before being available for general users, Stata programs (i.e.
those availabe in SSC or elsewhere) are extensively validated? As a
reviewer, should one trust 100% in new user written Stata programs?
It is worth of mentioning that, by no means, I am doubting the reliability
of Stata user-written programs. [Btw, I thank you all for your hard work
to make freely available several important programs]. I just want to
discuss a way to make packages more clear to avid Stata users like me and,
as result, improve the quality of Stata.
When no reference is provided, one has to open the .ado file, check the
formulae and try to figure out which method (and paper) was used to write
the program. If you do not know a little bit of Stata programming (that
goes a long way :-), you may write an email to the author and, usually,
when s/he does not reply, you get almost crazy.
Hence, it would be nice if Stata programmers could add to the help file a
complete list of reference, preferentially mentioning in detail which
formulae was used and providing an example already used/presented in
classic papers or text books.
Sincerely yours,
Tiago Pereira
*
* 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/
