|
Thank you all , I will focus on -xtreg- then.
Ivan
-------Original Message-------
Date: 11/23/07 02:08:02
Subject: Re: Re: xtabond with N equal to T
In Alvarez and Arellano (2003) you could see that WG (xtreg, fe) is
recommended for your case.
Rodrigo.
Alvarez and Arellano (2003) "The Time Series and Cross-Section Asymptotics
of Dynamic Panel Data Estimators", Econometrica 71, 1121-1159
----- Original Message -----
Sent: Thursday, November 22, 2007 9:21 AM
Subject: st: Re: xtabond with N equal to T
> xtabond works from the Arrellano and Bond paper "Some Specification Tests
> for Panel Data: Monte Carlo Evidence and an Application to Employment
> Equations" (1991), Review of Economic Studies.
>
> One of their first assumptions is that T is small and N is large. Now,
> your sample of N=20 and T=20 tends to go against this.
> **********************************************
> ----- Original Message -----
> From: Ivan Etzo
> Sent: Thursday, November 22, 2007 11:03 AM
> Subject: st: xtabond with N equal to T
>
>
> Dear all,
>
> I'm working with a panel with N=20 and T=20, do you I should use xtabond?
>
> Thanks to everybody
>
> Ivan
> *
> * For searches and help try:
| 