Stata estimates Arellano and Bond (1991) but not Blundell and Bond (1998). The latter is available free for GAUSS. Try searching for DPD98 in a search engine and you should find it. Or it used to be on Arellano's homepage.
Kevin
-----Original Message-----
From: [email protected] on behalf of [email protected]
Sent: Mon 11/10/2003 10:28 PM
To: [email protected]
Subject: Re: st: RE: Blundell-Bond GMM estimator
Dear Kevin and Statalisters:
I am glad to have a reply to my question. Thank you very much for your swift
answer.
I am actually using the -xtabond- command for my regression exercise. However,
Arellano-Bond GMM estimator is biased in the presence of unit roots and suffers
from the weak instrument problem as the coefficient of lagged dependent variable
gets close to 1, as shown in Blundell and Bond (1998, JOE) where they proposed
an alternative estimator. If there is no STATA version of Blundell-Bond
estimator procedure, I would be interested in getting GAUSS version. Please
anybody has the procedure kindly help me. Many thanks.
_______________________________________________________
Byungdoo Sohn
Sr Economist, Development Economics Vice Presidency(DECVP)
The World Bank, 1818 H St. N.W. Washington, DC, 20433 USA
[MSN] MC4-404 [RmN] MC4-346 [Email] [email protected]
[Phone] 202 473 6784 [Fax] 202 522 1158 [Mobile] 703 589 7456
________________________________________________________
"Amess, Dr K.M."
<[email protected]> To: <[email protected]>
Sent by: cc:
owner-statalist@hsphsun2. Subject: st: RE: Blundell-Bond GMM estimator
harvard.edu
2003-11-10 03:45 PM
Please respond to
statalist
Use the -xtabond- command in versions 7 or 8. Although I think this is a useful
addition to Stata's capabilities, I personally prefer the GAUSS version of the
programme Arellano wrote because one has greater flexibility over the instrument
set used.
Kevin
-----Original Message-----
From: [email protected] on behalf of [email protected]
Sent: Mon 11/10/2003 3:47 PM
To: [email protected]
Subject: st: Blundell-Bond GMM estimator
Dear Statalisters:
I think the same question was posted by someone else quite a while ago, but I
couldn't find the answer. I am wondering if there is anybody who has the STATA
do file to compute Blundell-Bond dynamic panel GMM estimator. If so, please let
me know. Thank you in advance for your help.
_______________________________________________________
Byungdoo Sohn
Sr Economist, Development Economics Vice Presidency(DECVP)
The World Bank, 1818 H St. N.W. Washington, DC, 20433 USA
[MSN] MC4-404 [RmN] MC4-346 [Email] [email protected]
[Phone] 202 473 6784 [Fax] 202 522 1158 [Mobile] 703 589 7456
________________________________________________________
*
* 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/
(See attached file: winmail.dat)
<<winmail.dat>>
