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]

Re: st: ivreg2 and endogeneity


From   Michele Mancini <mikmancinistata@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   Re: st: ivreg2 and endogeneity
Date   Thu, 23 Jun 2011 23:08:34 +0200

Thank you for your help. X1, X2, X3 and X4 should be very good instruments.
The t-test for these in the first step are above 40 in every case.
So they're not weakly identified and I look at the overid test of all
instruments, saying that something's wrong because the null is
rejected.
I think that the exclusion restrictions are fine because they're also
used in the literature.
If I treat X1 as an included instruments I get:  X1 is not
significant, Hansen reject the null and the endogeneity is not true.
If I drop X1 I get: the others instruments are not weak, Hansen accept
the null and the endogeneity is true.
Should I drop X1 and conclude that fd is endogenous? I can't manage to
solve this question.
Thanks again

Michele Mancini

2011/6/23 Austin Nichols <austinnichols@gmail.com>
>
> Michele Mancini <mikmancinistata@gmail.com>:
> First, think through theory--is X1 really a good instrument?  Are X2, X3, X4?
>
> But also, as a rough guideline, look at stats in this order:
> First, look at id stats.  If not weakly identified, then overid test
> may have good power.
> Second, look at overid test.  If can't reject null, maybe endogeneity
> test has good power.
> Third, look at endogeneity test.  If reject exogeneity, we prefer IV.
>
> Note that an endogeneity test is a measure of whether IV differs from
> OLS, so if you
> are using bad exclusion restrictions, your IV may not differ from OLS
> not because
> there is no endogeneity problem but because your IV assumptions are wrong.
>
> It looks to me like X1 is simply not a valid excluded instrument and
> should not be used as such.
> Perhaps it should be an included instrument, i.e. a control variable?
>
> On Thu, Jun 23, 2011 at 4:28 PM, Michele Mancini
> <mikmancinistata@gmail.com> wrote:
> > Dear Statalisters,
> > I have some questions regarding my ivreg2 estimation:
>
> > My question is the following: as you can see the endogeneity test says that
> > fd in actually exogenous and the Hansen J statistic strongly reject the
> > null; should I treat fd as exogenous and use OLS instead of IV? The problem
> > is that if I remove X1 from the instruments
>
> > How can i interpret these results of the C statistics? Should I drop X1 and
> > treat fd as endogenous? Or using OLS instead of IV?
> > Thank you so much for your kind help.
> > Regards,
> >
> > Michele Mancini
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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