st: Time-varying characteristics in a Panel Data.

[natasha agarwal <agarwana2@googlemail.com>]

Dear statalist,

I have an unbalanced panel data on 15,000 firms for 5 years. I am
estimating a Cobb Douglas production function using a within estimator
with robust standard errors.

I understand that the within estimator would take care of the
unobserved time-invariant firm-level factors. However, I also wanted
to account for time-varying firm-level factors for which I wanted to
include firm*year dummies in the specification.

However, when I generate firm*year dummies and include in the
specification, I have allot of firm*year estimated coefficients and it
probably takes me over a day to estimate the same.

Is there any way in stata that I can deal with it more efficiently?

Many thanks in advance.
Natasha
*
*   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/