Without disagreeing with you, I think the StataCorp
line is that
1. the more technical stuff should go in the manuals.
2. they want the help files to be as lean as possible.
3. they want you to buy the manuals.
4. people who want this are usually smart enough
to work backwards from -*ret li- and some output
(not that this detective work should be imposed
on you, just that you do have this possibility).
Nick
[email protected]
McKenna, Timothy
> Why is it set up like that? The names of the returned results are one
> of those things that isn't conceptually hard, but easy to
> forget. This
> is precisely the kind of info I would like to have in the online help,
> similar to how the syntax (also easy to forget) is put into the online
> help.
Nick Cox
> This is not quite true. The official Stata standard is
> to document returned results in the manual, not
> the help file.
Kit Baum
> > please note that -help ivreg2- (like all well-
> > documented Stata routines) lists all of the dozens of
> return values
> > that are available: e.g.
> >
> > ...
> > e(sargan) Sargan statistic
> > e(sarganp) p-value of Sargan statistic
> > e(sargandf) dof of Sargan statistic = degree of
> > overidentification = L-K
*
* 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/
