Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: F-statistic on ivreg2 vs ivreg with clustering


From   Robert Duval <rduval@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: F-statistic on ivreg2 vs ivreg with clustering
Date   Wed, 18 May 2005 00:01:49 -0400

Dear all,

When I run the ivreg2 command with the "robust cluster()" options
(without the gmm option) I get a different Fstatistic than the one I
get with ivreg. Can anybody explain why?

In particular when I run

ivreg Dearn15 (rearn=age age2 eduyr eduyr2 sexo cavern) if filtro1==1,
robust cluster(clust)

I get an  F(  1,   615) =   11.13
            Prob > F      =  0.0009


While if I do

 ivreg2 Dearn15 (rearn=age age2 eduyr eduyr2 sexo cavern) if
filtro1==1, robust cluster(clust)

I get an  F(  1,   614) =     1.60
             Prob > F      =   0.2068


I checked that this only occurs when the option "cluster" is included,
otherwise the output is the same under both commands.

This is not the result of gmm (because I didn't specify that option),
nor the result of any small sample correction.

If anybody with knowledge of ivreg2 can help me out why the output is
different under these commands I would greatly appreciate it.

Robert

*
*   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/



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