[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Hausman Test when the RE OLS model includes time-constant variables

From   "Rodrigo Alfaro A." <>
To   "Pavlos C. Symeou" <>
Subject   st: RE: Hausman Test when the RE OLS model includes time-constant variables
Date   Thu, 17 Apr 2008 15:06:14 -0400


We are in the same page, but you are not considering that "maybe" your
x's have very small within variation, then they could be not significant
in the FE model but significant in the RE model. Anyway, not significant
variables is not bad because of that, it is bad for your research
question. I am thinking in a econometric way to fit the data instead of
doing data mining. In addition, I did not argue about your r2, which I
do not know the type that you are reporting here (within, overall,
between?). I suggested you to look on the importance of the variance of
the random component. Even more, you provided evidence that FE was
"accepted" against RE without these cross dummies. For these reasons, I
am still more favorable for FE than RE. It is a huge task convincing to
referees that random effects is appropiate because RE is not a robust
model in the set of specifications that you have. 

Anyway, what are the variables behind your model, maybe other members
could provide a standard procedure for your specific data, such
education, economics, etc.


-----Mensaje original-----
De: Pavlos C. Symeou [] En nombre de Pavlos
C. Symeou
Enviado el: Jueves, 17 de Abril de 2008 02:48 p.m.
Para: Rodrigo Alfaro A.
Asunto: Re: Hausman Test when the RE OLS model includes time-constant


Thanks for your reply. I understand that there might be correlation
between the random effect and x(i,t) using the RE. However, the RE model
on the one hand allows me to include the industry dummies (crucial for
the model's specification) and on the other hand most coefficients are
statistically significant and support my theoretical arguments. To the
contrary, in order to include the industry dummies in the FE model, I
need to create interactions and even if I do that, the model hardly
explains any relationship as all of my coefficients are statistically
insignificant. In addition, the RE reports much higher R-squares (around
0.3) than the FE (around 0.02). Is there a way that I can account for
this correlation whilst maintaining my existing (and only) variables in
the model?



ADVERTENCIA: La  información  contenida  en  esta  transmisión, y  en  cualquier archivo  adjunto, está  sujeta a reserva legal conforme a la normativa aplicable  al  Banco  Central  de  Chile, y  no  puede  ser usada o difundida  por personas distintas  de  su o sus destinatarios. Si usted ha recibido esta transmisión por error,  por  favor  notifique  inmediatamente al remitente respondiendo por este mismo medio y elimínela de su sistema.
El  Banco Central de Chile no se hará responsable de la exactitud y veracidad de la información contenida en este mensaje, así  como  de su  modificación, copia, divulgación  o  reenvío,  total  o  parcial.   Su  uso  no  autorizado puede ser sancionado de conformidad con las leyes chilenas. 
El  Banco  Central  de  Chile  transmite  sus decisiones a través de comunicados oficiales, los  que  pone  a  disposición  del público en su página de Internet: 

DISCLAIMER: The information  contained  in  this  email or any attached file, is subject to legal  privilege  pursuant  to the laws and regulations applicable to the Central  Bank  of  Chile , and may not be used or disseminated by any person other  than  its  intended recipients. If you have received this transmission in error, please  notify  the sender immediately by reply to this email address and delete it from your system.
The Central Bank  of  Chile shall not be liable for the accuracy or authenticity of the contents of this message, whether amended, copied, forwarded or disclosed in  any  form, in  whole  or  in part.  Please note that unauthorized use may be penalized  in  conformity  with  the  Chilean law.    
The Central  Bank of Chile communicates its decisions by  official releases, and 
makes them available to the public in its WebPages:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index