Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: overid


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: overid
Date   Tue, 30 Oct 2007 19:33:39 -0000

Orgul,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Orgul Demet Ozturk
> Sent: 30 October 2007 14:23
> To: statalist@hsphsun2.harvard.edu
> Subject: st: overid
> 
> Hi,
> I am  using overid test but I am rather confused about it is 
> implications.
> (I copy-pasted the regression and test results at the bottom 
> of this message) According to the test result I am not 
> rejecting my null which means ?
> I am not perfectly sure what the null is in this case.

This is covered in all standard econometrics textbooks. The help file of
-ivreg2- has a short description, and the 2003 paper by myself, Kit Baum
and Steve Stillman (see the references section of the -ivreg2- help
file) discusses it.  In short, the null is that your instruments are
uncorrelated with the error, and rejection of the null suggests the
instruments aren't valid.  You don't reject the null, so - good news for
you!

Note, by the way, that in your output the Sargan stat reported by
-ivreg2- is identical to the first stat reported by -overid-.  Same
test.

> Also,
> Can you please tell me  if there is  any underidentification 
> test I can use with ivreg2.




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