st: Data envelopment analysis for Panel Data

[Sarfraz Khan <sarkhan3@gmail.com>]

Hello All:

I have a big panel dataset (150,000 observations) and I want to use DEA
methodology to calculate efficiency of lets say production (with production
as output and four other input variables). However, my problem is that I
want to do that for every 2-digit industry code. I am wondering if there is
an efficient way to do so.

Following is the command I would use if I need to do it for 5 firms in an
year.

dea input = output, sav(eff_results)
use eff_results, clear
tobit theta independent_variables, ul(1)

Can someone please help me expand the above set of commands and use it in
the setting that I describe above.

Thanks,
Sarfraz
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/