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

RE: st: Problems Stochastic Frontier Analysis


From   [email protected]
To   [email protected]
Subject   RE: st: Problems Stochastic Frontier Analysis
Date   Tue, 3 Feb 2004 17:43:54 +0100

Dear David

thanks for your comment. It helps. But I have still a strange thing. If you
look at the z-values. You see very high values. Above 100.000. If I
estimate the same model specifications with Limdep I get normal z-values
(around 3). The coefficients in Limdep and Stata are almost the same. What
can explain  the enormous large z-values.

regards

erik brouwer


                                                                                                                                              
                      "David M. Drukker,                                                                                                      
                      StataCorp"                      To: [email protected]                                                      
                      <[email protected]>            cc:                                                                                     
                      Sent by:                        Subject:  RE: st: Problems Stochastic Frontier Analysis                                 
                      owner-statalist@hsphsun2.                                                                                               
                      harvard.edu                                                                                                             
                      03/02/2004 17:01                                                                                                        
                                                                                                                                              
                      Please respond to                                                                                                       
                      statalist                                                                                                               
                                                                                                                                              
                                                                                                                                              




Eric Brouwer <[email protected]> wrote that he was having trouble
performing Stochastic Frontier Analysis in Stata.

After the estimation command

. frontier lnTK lnZT, d(e) cost;

that produced

Stoc. frontier normal/exponential model           Number of obs   =
15
                                                  Wald chi2(1)    =
1.115e+12
Log likelihood =  8.5130782                       Prob > chi2     =
0.0000

------------------------------------------------------------------------------

        lnTK |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
-------------+----------------------------------------------------------------

        lnZT |   1.244566   1.18e-06        .   0.000     1.244563
1.244568
       _cons |  -4.327623   .0000181        .   0.000    -4.327659
-4.327588
-------------+----------------------------------------------------------------

    /lnsig2v |  -39.73655   977.6138    -0.04   0.968    -1955.824
1876.351
    /lnsig2u |  -3.135077   .5163978    -6.07   0.000    -4.147198
-2.122956
-------------+----------------------------------------------------------------

     sigma_v |   2.35e-09   1.15e-06                             0
.
     sigma_u |   .2085579   .0538494                      .1257324
.3459441
      sigma2 |   .0434964   .0224614                     -.0005272
.08752
      lambda |   8.87e+07   .0538494                      8.87e+07
8.87e+07
------------------------------------------------------------------------------

Likelihood-ratio test of sigma_u=0: chibar2(01) = 7.84   Prob>=chibar2 =
0.003

Eric typed

. predict lnTKhat;
(option xb assumed; fitted values)
. predict xb;
(option xb assumed; fitted values)
. predict u;
(option xb assumed; fitted values)
. predict te;
(option xb assumed; fitted values)

He then noted that LnTKhat, xb, u, and te all had the same values.  The
problem is that Eric has not specified the options to predict for u and te.
He only gave the variables different names.

If Eric were to try

. frontier lnTK lnZT, d(e) cost;

. predict xb, xb

. predict u, u

. predict te, te

He should find that the new variables now contain the linear (xb)
predictions, the estimates of minus the natural log of the technical
efficiency via E[u_i|e_i], and estimates of the technical efficiency via
E[exp(-su_i)|e_i], respectively.

I would also like to suggest that Eric take a look at the manual entry for
the formulas that are used in computing xb, u, and te.

--David
  [email protected]

*
*   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/



_________________________________________________________________
The information transmitted is intended only for the person or entity to
which it is addressed and may contain confidential and/or privileged
material.  Any review, retransmission, dissemination or other use of, or
taking of any action in reliance upon, this information by persons or
entities other than the intended recipient is prohibited.   If you received
this in error, please contact the sender and delete the material from any
computer.


*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index