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

st: Re: Re: ivreg2 extensions


From   "Luis Fernandes Rodrigues" <nop44660@netcabo.pt>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Re: ivreg2 extensions
Date   Thu, 7 Aug 2003 16:44:51 +0100

Thanks to the fast feed-back of the ivreg2 team,

I am quite familiar with the work of Arellano and Bond, particularly with
several versions of DPD in Gauss and Ox. It seems to me that xtabond is more
limited than the last versions available in the DPD package (where I can use
single estimation methods for panel data still not available in  Stata),
because xtabond demands that your model contains a lagged dependent variable
and my models are not dynamic.

That's why I am so interested in the work of your team intends to implement
a variety of heteroskedastic and autocorrelation-robust estimators for
single-equation IV/GMM estimation that can goes beyond the work available so
far.



I hope that you Mark and Steven enjoy your holidays.



Luis



----- Original Message ----- 
From: "Kit Baum" <baum@bc.edu>
To: <statalist@hsphsun2.harvard.edu>
Sent: Thursday, August 07, 2003 2:24 PM
Subject: st: Re: ivreg2 extensions


> On Thursday, Aug 7, 2003, at 02:33 US/Eastern, Luis wrote:
>
> > In the end of your reply you stressed that a version of ivreg2 is
> > currently
> > under development which will provide 'ivgmmN', allowing for arbitrary
> > heteroskedasticity and serial correlation in the error process.
> >
> > This will be a enormous help for the research four which I need to go
> > frequently out of Stata. Do you know something more about its
> > availability
> > or other GMM procedures already available?
>
> I am not aware of other GMM procedures currently available, beyond
> those provided by xtabond. The routine I mention is being tested by the
> ivreg2 team, spread over three continents and diverse holiday
> schedules. I cannot predict when it will be ready for release, although
> I would hope that we will have a fully-documented and reasonably well
> tested version to circulate in September. Obviously with these things
> getting it right is more important than getting it out the door (unless
> you're a convicted monopolist).
>
> Thanks for your interest in our work.
>
> Kit
>
> *
> *   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/



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