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

Re: st: dynamic panel estimation in the presence of unit roots


From   "alopca2002" <alopca2002@yahoo.es>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: dynamic panel estimation in the presence of unit roots
Date   Tue, 11 Nov 2003 16:17:37 -0000

Dear Dann and statalist users;

I have read the Blundell and Bond paper (JOE 87, 1998)about the
validity of the GMM estimator developed by Arellano and Bond in 1991.
Actually i have some doubts about the interpretation of the Monte-
Carlo simulations attached. It seems that there is a little gain when
N=500 and T=11.

I am working with a panel data of N=604 and T=8 and i obtain an high
value of alpha, above 0.8. Is it worth to estimate the Blundel-Bond
model using DPD with so huge database? Also, are the Arellano-Bond
results biased in my model?

All sugestions are welcome!!!!!!

Thanks in advance.

Faithfully yours
Alfredo Lopez
Business and Management Department
University of Zaragoza
Zaragoza (Spain)
--- In statalist@yahoogroups.com, "Millimet, Daniel" <millimet@m...>
wrote:
> You may want to at least see the work by blundell and bond, I
believe in
> Econometric Reviews, around 2000-2002.  they show that the arellano-
bond
> estimator is biased when the coefficient on the lagged dependent
var.
> gets even reasonably close to 1 (anything above about 0.7).  They
> propose an alternative estimator that is available in gauss.  I'm
not
> sure what happens to that revised estimator if in fact there is a
unit
> root.  I imagine it fails.
>
> Dann
>
> ----------------------------------------------------------------
> Daniel L. Millimet, Assistant Professor
> Department of Economics
> Box 0496
> SMU
> Dallas, TX 75275-0496
> e-mail: millimet@m...
> phone: 214.768.3269
> fax: 214.768.1821
> web: http://faculty.smu.edu/millimet
> ----------------------------------------------------------------
>
>
> > -----Original Message-----
> > From: Dev Vencappa [mailto:lexdvv@n...]
> > Sent: Friday, October 10, 2003 7:53 AM
> > To: statalist@h...
> > Subject: Re: st: dynamic panel estimation in the presence of
> > unit roots
> >
> >
> > Statalist, is there anybody who knows of relevant literature
> > on what are the consequences of estimating dynamic panels
> > when the variables have unit roots and what are the
> > consequences for that? (and any possible implementation in Stata)
> >
> > Any suggestions please?
> >
> > Dev
> >
> >
> > Dev Vencappa
> > School of Economics
> > University of Nottingham
> > University Park
> > Nottingham
> > NG7 2RD
> > U.K.
> > Tel : +44 (0)115 951 5608
> > Fax: +44 (0) 115 951 4159
> >
> > *
> > *   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/



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