Re: st: estat firststage after using vce(cluster id)

[Roberto Liebscher <roberto.liebscher@ku.de>]

I think in the case of clustered standard errors the iid assumption is 
violated. Hence the F statistic is not appropriate anymore.

I also found a general discussion about that here:

http://www.stata.com/statalist/archive/2005-12/msg00583.html

Kind regards,
Roberto

--
Roberto Liebscher
Catholic University of Eichstaett-Ingolstadt
Department of Business Administration
Chair of Banking and Finance
Auf der Schanz 49
D-85049 Ingolstadt
Germany

Am 14.02.2013 00:53, schrieb D-Ta:
> Dear statalisters,
>
> I am using the -ivregress- command with clustered standard errors in 
> the following form:
>
> ivregress 2sls y x1 x2  (t=z ) if adult==1, first vce(cluster id)
>
> I then use -estat firststage- where I would like to save the F-stat of 
> the first stage by -local fstat `r(mineig)'-
>
> The latter works, as long as I dont use clustered standard errors in 
> the regression, as soon as I do use them, there is no F-stat provided 
> by the -estat firststage- .
>
> Can someone explain me why and if there is a way to get the F-stat 
> despite clustered standard errors?
>
> Many thanks,
> Darjusch
>
>
>
>
>
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/