Thanks Mark, I will give that a shot.
Best,
Raymond
PS - Yes, sorry about the lack of subject line. I realized I'd forgotten to
write it about 1 millisecond after hitting "send".
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Schaffer, Mark E
Sent: Wednesday, April 02, 2008 7:26 PM
To: [email protected]
Subject: st: Cragg-Donald-Stock-Yogo critical values (was RE: Date: Wed, 2
Apr 2008 18:36:19 -0400)
Raymond,
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> Raymond Guiteras
> Sent: 02 April 2008 23:37
> To: [email protected]
> Subject: st: Date: Wed, 2 Apr 2008 18:36:19 -0400
>
> Dear Statalist,
>
> I am using the excellent --ivreg2-- to test for weak
> instruments. I would like to use the Stock-Yogo critical
> values that are displayed but do not see an ereturn scalar or
> matrix that corresponds to these values. Is there a way to
> extract these?
This facility doesn't exist, though it's a good suggestion and worth
considering for a future version.
That said, you can easily extract the code for the critical values from
ivreg2.ado and create your own Stata program to look them up. Near the
bottom is a block of code that starts
program define cdsy, rclass
and ends with (surprise)
end
Copy this block of code into a file called cdsy.ado
(Cragg-Donald-Stock-Yogo), save it in your personal ADO folder, and you
have an rclass program that finds the critical value and leaves it in
r(cv). A typical call would be
cdsy, type(xxx) k2(yyy) nendog(zzz)
where
type() can be "ivbias5" (or 10, 20, 30), "ivsize10" (or 15, 20, 25),
"limlsize10" (or 15, 20, 25), "fullrel5" (or 10, 20, 30), "fullmax5" (or
10, 20, 30).
k2() is the number of excluded exogenous variables
nendog() is the number of endogenous regressors
Thus
. cdsy, type(ivbias5) k2(6) nendog(2)
. return list
scalars:
r(cv) = 15.72
Or after a call to -ivreg2-,
. cdsy, type(ivbias5) k2(`e(exexog_ct)') nendog(`e(endog_ct)')
. return list
scalars:
r(cv) = 15.72
Cheers,
Mark
NB: You should try to use a more informative subject line next time.
Postings to Statalist with the subject "Date: Wed, 2 Apr 2008 18:36:19
-0400" are not designed to attract wide interest!
> I am using the following version of ivreg2:
> e(version) :
> "02.2.08", which I believe is the most recent. I apologize in
> advance if I am missing something obvious or if this has been
> discussed before; my search of the archives & online help did
> not turn up an answer to this question.
>
> Many thanks,
> Raymond
>
> PS - I attempted to post this yesterday evening (EDT) but as
> far as I can tell it did not make it to the list (i.e. it has
> not yet shown up in either archive). I apologize if this is
> (or becomes) a duplicate post.
>
> *
> * 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/
>
--
Heriot-Watt University is a Scottish charity
registered under charity number SC000278
*
* 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/
*
* 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/
