Tom,
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> Thomas Mayock
> Sent: Thursday, December 13, 2007 12:36 PM
> To: [email protected]
> Subject: Re: st: RE: Endogenous Panel Estimation
>
> Mark,
> Many thanks for your help. I have been able to run the
> overid test with the RE model, but I keep getting an error
> for the first stage estimates that reads "Unable to display
> summary of first-stage estimates; macro e(first) is missing."
> Following the commands "xtivreg (insert specification), re"
> , I included the line "xtoverid, noid". I believe you
> suggested this in another post I came across on the list. It
> almost looks as if this could be a problem in the call to
> ivreg2. Have you come across this before?
The option is -noi- (for -noisily-), not -noid-. However, -noi- is
undocumented because it's there to help me debug things, and so it's not
guaranteed to work for anybody (including me!).
If the -noi- option works, great, you should get first-stage stats as
well as an overid stat; if not, then drop it and you'll get just the
overid stat. I hope this is good enough for your purposes.
Cheers,
Mark
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University
Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3296 fax
http://www.sml.hw.ac.uk/cert
> Cheers
> Tom
>
> ----- Original Message -----
> From: "Schaffer, Mark E" <[email protected]>
> Date: Wednesday, December 12, 2007 6:17 pm
> Subject: st: RE: Endogenous Panel Estimation
> To: [email protected]
>
> > Tom,
> >
> > > -----Original Message-----
> > > From: [email protected]
> > > [mailto:[email protected]] On Behalf Of Thomas
> > > Mayock
> > > Sent: 12 December 2007 22:43
> > > To: [email protected]
> > > Subject: st: Endogenous Panel Estimation
> > >
> > > Hello to all,
> > > I am somewhat new to Stata, so please forgive my ignorance
> > > should the answer to my question be painfully obvious to the more
> > > experienced.
> > > I am estimating a random effects panel model, and I believe
> > > that some of the time-invariant regressors are
> endogenous. I have
> > > experimented with xtivreg and xtivreg2, but I have not
> figured out a
> > > (simple) way to test for overidentifying restrictions or
> perform the
> > > standard first-stage joint significance test. I know these are
> > > options for the fixed effects model. Is there another
> routine out
> > > there that may allow for these tests?
> >
> > -xtoverid-, available from SSC (as soon as it's back up
> again!), will
> > do an overid test after xtivreg with random effects.
> >
> > Cheers,
> > Mark
> >
> > Prof. Mark Schaffer
> > Director, CERT
> > Department of Economics
> > School of Management & Languages
> > Heriot-Watt University, Edinburgh EH14 4AS tel
> +44-131-451-3494 / fax
> > +44-131-451-3296
> > email: [email protected]
> > web: http://www.sml.hw.ac.uk/ecomes
> >
> >
> > > I have
> > > searched around the internet a bit, but I have yet to come across
> > > anything. I just wanted to try the board about before
> cranking this
> > > out in Matlab.
> > > Thanks in advance for any help.
> > > Best,
> > > Tom
> > > *
> > > * 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/
> > >
> >
> > *
> > * 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/
> >
> *
> * 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/
>
*
* 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/
