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

RE: Macoreconometric dynamic panels (was: Re: st: panel autocorrelation)


From   "Salvati, Jean" <JSalvati@imf.org>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: Macoreconometric dynamic panels (was: Re: st: panel autocorrelation)
Date   Mon, 18 Oct 2004 10:55:19 -0400

Edlira,

You can use xtabond or xtabond2.

The estimators implemented in these two commands are still valid when
x_(it-1) is used as a regressor, if that's what you're worried about. By
using x_(it-1) as well x_(it) you loose a good instrument for x_(it),
but that's only a concern if x_(it) is not exogenous, and it doesn't
make the estimator inconsistent anyway.

If you're worried about the xtabond estimator's consitency for N=33,
T=23, check out the paper by Alvarez and Arellano (2003), "The
time-series and cross-section asymptotics of dynamic panel data
estimators", Econometrica, July. Consistency of the GMM estimator
implemented in xtabond was initially established under the assumptions T
fixed, N->infinity, or "small T, large N", which doesn't seem to apply
to your sample. But Alvarez and Arellano have also shown this estimator
to be consistent for T/N->c with 0<c<=2. 

Also, keep in mind that, as p increases in your model, you also loose
some periods and some instruments.

Jean Salvati
Econometric Support
(202) 623-7804
IS 12-1328
 

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Edlira Narazani
> Sent: Monday, October 18, 2004 8:18 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: Macoreconometric dynamic panels (was: Re: st: 
> panel autocorrelation)
> 
> Dear all,
> 
> I have a model like this:
> y_it =  y_(it-1)a_1 + ... + y_(it-p)a_p + x_(it)b_1 + 
> x_(it-1)b_2+ w_(it)b_2 +
> v_i + e_(it)      i={1,...,33};     t={1,...,23_i},
> 
> I know that xtabond command could be used in case of :
> 
> y_it =  y_(it-1)a_1 + ... + y_(it-p)a_p + x_(it)b_1 + 
> w_(it)b_2 + v_i + e_(it)  
>    i={1,...,N};     t={1,...,T_i},
> 
> Should I use xtabond command even in my case? Otherwise what 
> command could be helpful to estimate the parameters?
> Thanks
> Edlira
> 
> 
> 
> ----------------------------------------------------------------
> This message was sent using IMP - Facolta' di Economia - Torino.
> 
> *
> *   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