Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: How to -estadd- specific F statistics after -ivreg2- ?


From   Jen Zhen <jenzhen99@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: How to -estadd- specific F statistics after -ivreg2- ?
Date   Wed, 26 Jun 2013 18:50:17 +0200

Dear Statalisters,

I am using Baum-Schaffer-Stillmann's -ivreg2- to conduct 3 different
(in terms of covariates/included instruments) IV regressions, each
with 2 excluded instruments,
and then I use Ben Jann's -esttab- to tab first the IV results, then
the reduced form results, and then the first stage results:

eststo: ivreg2 outcome (endogreg = ins1 ins2) covar1, robust savefirst
savefprefix(first1) saverf saverfprefix(rf1)
eststo: ivreg2 outcome (endogreg = ins1 ins2) covar2, robust savefirst
savefprefix(first2) saverf saverfprefix(rf2)
eststo: ivreg2 outcome (endogreg = ins1 ins2) covar3, robust savefirst
savefprefix(first3) saverf saverfprefix(rf3)

esttab est*  using "iv.csv", r2 se replace lines compress se(%-9.2f)
stats(r2 jp N)
esttab rf*    using "iv_rf.csv", r2 se replace lines compress se(%-9.2f)
esttab first* using "iv_fs.csv", r2 se replace lines compress se(%-9.2f)

Now I would like to include in the -esttab- commands for the first
stage a line that contains the F statistic from testing the joint Null
that the 2 instruments have a zero effect.
And, relatedly, I would like to include in the -esttab- of the reduced
form the joint Null that the reduced-form effects of the 2 instruments
are both zero.



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