Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

st: fixed effects estimation with unbalanced panel

From   Eric Walcott <>
Subject   st: fixed effects estimation with unbalanced panel
Date   Tue, 26 Mar 2013 12:44:52 -0400

I'm having an issue with fixed effects estimation of an unbalanced panel.
Due to various issues, mostly related to the smallness of my dataset, when
I run fixed effects including the year dummies and cluster robust standard
errors, STATA won't calculate the F statistic for the model. If I remove
the year dummies or I run the regression without cluster-robust SE it
works, but then I'm losing important parts of the model. The year dummies
are jointly significant, so I don't want to remove them, but I also need
cluster robust standard errors to control for heteroskedasticity and serial
correlation that I have in my data. Any suggestions on how I should handle
this? Is there a way around this problem, or do I have to choose between
year dummies and cluster-robustness?

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index