Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: effects size in pooled ols, random and fixed effects models
From
Volker Ludwig <[email protected]>
To
[email protected]
Subject
st: effects size in pooled ols, random and fixed effects models
Date
Tue, 21 Jun 2011 17:09:27 +0200
Hello Listers,
I estimated three linear models with panel data: pooled OLS, random
effects and fixed effects.
The specification is very simple, including just one covariate and time
dummies.
The coeffcients are, however, not as expected.
As I understand it, the size of the coeff from the RE model must always
be in between the other two models because only part of the within-mean
is substracted.
In my model, this is not the case. (The RE coeff is smallest). Any ideas
why?
Many thanks
Volker
________________________
Volker Ludwig
Universität Mannheim
Mannheimer Zentrum für Europäische Sozialforschung (MZES)
D-68131 Mannheim
phone +49-621-181-2849
fax +49-621-181-2803
[email protected]
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/