Hi Valerio.
As a co-author of ivreg2, I'll apologise for the slight ambiguity in the help-file. ivreg2 does not estimate fixed effects or random effects panel data models. it is able to produce standard errors that account for autocorrelation within panels hence the line in the help file.
Unfortunately, the advance features you are looking for do not mesh well with the random effects estimator, hence the reason why xtivreg2 does not deliver in this area. My co-author, Mark Schaffer, has spent some time trying to code up these features for random effects models, but I do not know how much progress he has made in this area. He is active on statalist, so will likely respond to this email once he gets the chance.
Cheers,
Steve
-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of valerio
ercolani
Sent: Friday, July 07, 2006 1:06 AM
To: [email protected]
Subject: st: ivreg2
question regarding ivreg2:
STATA help says "ivreg2 may be used with time series or panel data, in which
case, the data must be tsset before using ivreg2"
it means that ivreg2 can handle panel data, but: which kind of panel estimator
ivreg2 will deliver??? I assumed that it does a random effect est., indeed, if
i do xtivreg,re on the same data i obtain the same coefficients. Clearly, i
would prefer to use ivreg 2, instead of xtivreg,re, since with the first method
i can utilize a lot of options regarding residuals.
NOTE: i can't use xtivreg2 since xtivreg2 does not deliver re estimator, just
FE or FD!!!
thank you
Valerio
*
* 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/
