st: RE: XTIVREG first-stage F-statistic

["Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>]

Nicole,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nicole Au
> Sent: 22 October 2010 01:26
> To: statalist@hsphsun2.harvard.edu
> Subject: st: XTIVREG first-stage F-statistic
> 
> Dear all
> 
> I am using XTIVREG to estimate an instrumental variables 
> random effects model with 3 waves of panel data.
> Does anyone know how I can obtain the F-statistic of the 
> instruments in the first-stage regression?

xtivreg has a -first- option.  If you've got a single endogenous
regressor, you can take the t or z stat (I think it's a z stat) from the
first stage regression and manipulate it to get a first-stage F stat.

If that doesn't work ... I have an undocumented but mostly working
version of xtivreg2 that does random effects estimation.  If you contact
me off-list, I can send it to you.

Best wishes,
Mark

> 
> I understand xtivreg2 displays the F-stat for fixed-effects 
> or first-differences IV models, however there is no random 
> effects option for xtivreg2.
> 
> Thanks,
> 
> Nicole
> 
> 
> 
> *
> *   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/
> 


-- 
Heriot-Watt University is a Scottish charity
registered under charity number SC000278.


*
*   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/