Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: option predict te for cost frontier in stata 8.2


From   "Scott Merryman" <smerryman@kc.rr.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: option predict te for cost frontier in stata 8.2
Date   Mon, 20 Jun 2005 07:25:41 -0500

Yes, I believe Stata calculates efficiency as 

TE_i= E(Y_i|U_i, X_i)/E(Y_i|U_i=0, X_i) 
 
where Y_i is the production or actual cost of the i-th firm.  In a
production frontier efficiency will range from 0 to 1 while efficiency in
cost frontier will ranges from 1 to infinity.  This is how Coelli defined
efficiency (for instance, in "A Guide to FRONTIER Version 4.1" (1996))

However, Kumbhakar and Lovell (2000, "Stochastic Frontier Analysis") do
define cost efficiency as 

CE_i= E(Y_i|U_i=0, X_i)/E(Y_i|U_i, X_i)


Scott

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-
> statalist@hsphsun2.harvard.edu] On Behalf Of Dev Vencappa
> Sent: Sunday, June 19, 2005 7:58 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: option predict te for cost frontier in stata 8.2
> 
> >
> >
> Stata users,
>  I made a typo in the previous email which may have confused some users,
> so I'm posting it again.
>   I was running the frontier command for both a production and a cost
> function. While I understand that the option predict te retrieves the
> efficiency scores ranging between 0 and 1, when I was running the cost
> function I was a bit confused with the scores retrieved from the cost
> frontier. I got values ranging from close to 1 onwards, and I understand
> these need to be bound between 0 and 1. Am I right in assuming that the
> correct cost efficiency scores are just the inverse of the predicted
> efficiency scores from the predict te option? I suppose Stata is simply
> computing these scores in a similar way as for the production frontier,
> i.e. actual output/maximum output, so actual cost/minimum cost instead of
> minimum cost/actual cost?
> 
> Thanks in advance for any guidance on this.
> 
> Dev
> 


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index