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: RE: Fixed effects or random effects model?
From
"Jacobs, David" <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
st: RE: Fixed effects or random effects model?
Date
Fri, 6 Jan 2012 16:46:32 +0000
Paul Allison has one of those small Sage paperback publications on fixed-effects estimation. In it he shows a simple technique that allows one to estimate the effects of time-invariant explanatory variables. The coefficients on these variables, however, will not be estimated with fixed-effects.
D. Jacobs
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of sardar ahmad
Sent: Friday, January 06, 2012 10:47 AM
To: Statalist
Subject: st: Fixed effects or random effects model?
Dear all,
I am a PhD student and want to analyse Panel data. I have just started to learn about panel data analysis, so I apologise if my question is very basic.The data is for 8 years for 280 companies, I used Hausman test to decide whether to use fixed effects or random effects. The test shows that I should use fixed effects. However, I want to include a number of control variables which are constant over time e.g. industry in which a company is operating. As Stata drops such variables from the model, so I was wondering will it be justified to use random effects instead, even if the Hausman test is significant. Or are there any other alternatives?
Many thanks in advance.
Ahmad
*
* 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/
*
* 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/