As often pointed out on this list, it is
not a good idea to mess around with
official Stata ado files, even if you
think you know exactly what you're doing.
Also, you seem to be assuming that
an error recently reported will be
fixed retrospectively for Stata 7.
That is not the case. Stata 7
is history, especially so far as updates and fixes
are concerned, although StataCorp
will continue to provide tech support
to registered users. In some cases,
perhaps this one, that tech support
might consist of advising you that
the problem was fixed in Stata 8,
and so you would be advised to upgrade.
This is a brutal question, as people
who pay to upgrade don't want to see
scarce Stata resources devoted to
maintaining dead versions.
Anyway, I would have cloned -xtabond- under
another name if this were an issue under
Stata 8, but if my diagnosis is correct,
the -xtabond- you are using will be
exactly what it was, so only under
Stata 8, or through your programming,
will you able to explore the issue.
Nick
[email protected]
TEWODAJ MOGUES
> A while back I did some analysis with xtabond. I noticed a problem
> with the command and reported that on this list, after which a stata
> programmer confirmed the problem. Since then I have updated my Stata
> and my guess is that the updates reflect the fixed version of
> xtabond.
>
> Here is my question. I want to find out whether the difficulty I am
> having in replicating certain estimation results (using
> xtabond) I had
> found in the past is due to the fact that the old estimation was run
> on the faulty xtabond, or whether it'd due to something else such as
> change in the datase, etc.. To check for the first possibility, I
> tried to "un-update" xtabond on my Stata 7 by removing the ado files
> relating to xtabond from the folder stata/updates/ado/x/ . When I try
> to run the xtabond estimation after this removal, I get an error
> message saying "you are using an outdated version of xtabond. To
> update your ado-files, type -update ado- at the Stata prompt. r
> (499); ". How can I bypass such an error message and "force" stata 7
> to go ahead and use the unupdated xtabond?
>
*
* 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/
