st: fixed-effects with dummy variables

[bdeaton@uoguelph.ca]

Hello,

I have included dummy variables in a county-level fixed-effects regression.

Stata will estimate the coefficients for these dummy variables because  
they vary across time (as well as counties) in the sample.

Given the transformation of data in a fixed-effects regression, I am  
uncertain as to how I should interpret the coefficients for these  
dummy variables.

I�d greatly appreciate any thoughts/comments/ or suggested readings.

A simplified version of the county-level fixed effects regression I am  
running in stata is reflected by the following stata command:

xtreg  y d1 d2 d3  X t, fe

where:

y is a continuous variable
d1..d3 represent time varying dummy variables with the omitted dummy  
being (d4).
X represents a vector of time varying continuous explanatory variables.
t represents a vector of time dummy variables.


Thanks,

Brady Deaton
Food, Agricultural and Resource Economics
University of Guelph

P.S.  I posted a version of this question earlier in the week  
(received no responses). I believe, however, this current email better  
reflects my question and the range of advice that would be welcomed.





*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/