Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: Re: st: Residuals in Panel Data regression

From   DE SOUZA Eric <>
To   "" <>
Subject   RE: Re: st: Residuals in Panel Data regression
Date   Tue, 24 Apr 2012 16:58:18 +0200


FE treats the unobserved time invariant component as random and, therefor, requires strict exogeneity, which means that the lagged dependent variable is ruled out as a regressor. 
OLS with dummies (constants) only requires contemporaneous exogeneity and can include the lagged dependent variable as a regressor.


Eric de Souza
College of Europe
Brugge (Bruges), Belgium

-----Original Message-----
From: [] On Behalf Of Christopher Baum
Sent: 24 April 2012 15:42
Subject: Re: Re: st: Residuals in Panel Data regression

On Apr 24, 2012, at 2:33 AM, DD wrote:

> The key question here is: do the conditions/asumptions (regarding 
> error
> process) differ between OLS and FE??

They surely do not, because the FE estimator is conceptually just OLS with dummy variables for each unit in the panel.
However the meaning of 'robust' VCE changes, in that it should now be cluster-robust by panel unit, rather than standard White/sandwich estimator, as [xt] xtreg describes.


Kit Baum   |   Boston College Economics & DIW Berlin   |
                             An Introduction to Stata Programming  |
  An Introduction to Modern Econometrics Using Stata  |

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index