这是取对数后的结果: Error Components Frontier (see B&C 1992)
The model is a production function
The dependent variable is logged
the ols estimates are :
coefficient standard-error t-ratio
beta 0 0.30936882E+01 0.34323066E+00 0.90134377E+01
beta 1 0.64501474E-02 0.27730026E-01 0.23260517E+00
beta 2 0.65863985E-01 0.51742579E-01 0.12729166E+01
beta 3 0.74920760E+00 0.30256347E-01 0.24761998E+02
sigma-squared 0.39578661E+00
log likelihood function = -0.30948013E+03
the estimates after the grid search were :
beta 0 0.36470848E+01
beta 1 0.64501474E-02
beta 2 0.65863985E-01
beta 3 0.74920760E+00
sigma-squared 0.69717816E+00
gamma 0.69000000E+00
mu is restricted to be zero
eta is restricted to be zero
iteration = 0 func evals = 20 llf = -0.30339361E+03
0.36470848E+01 0.64501474E-02 0.65863985E-01 0.74920760E+00 0.69717816E+00
0.69000000E+00
gradient step
iteration = 5 func evals = 44 llf = -0.30304547E+03
0.34720646E+01-0.76109274E-02 0.75982777E-01 0.76615358E+00 0.70880087E+00
0.71353443E+00
search failed. loc of min limited by rounding
iteration = 9 func evals = 92 llf = -0.30301024E+03
0.34304773E+01-0.73617006E-02 0.73254217E-01 0.76840456E+00 0.68803626E+00
0.69636921E+00
the final mle estimates are :
coefficient standard-error t-ratio
beta 0 0.34304773E+01 0.32332497E+00 0.10609998E+02
beta 1 -0.73617006E-02 0.25862943E-01 -0.28464280E+00
beta 2 0.73254217E-01 0.49814341E-01 0.14705448E+01
beta 3 0.76840456E+00 0.28376671E-01 0.27078742E+02
sigma-squared 0.68803626E+00 0.89541684E-01 0.76839772E+01
gamma 0.69636921E+00 0.76314764E-01 0.91249606E+01
mu is restricted to be zero
eta is restricted to be zero
log likelihood function = -0.30301024E+03
LR test of the one-sided error = 0.12939790E+02
with number of restrictions = 1
[note that this statistic has a mixed chi-square distribution]
number of iterations = 9
(maximum number of iterations set at : 100)
number of cross-sections = 326
number of time periods = 1
total number of observations = 326
thus there are: 0 obsns not in the panel
以下是没有取对数,在ins里选n的结果:
Error Components Frontier (see B&C 1992)
The model is a production function
The dependent variable is not logged
the ols estimates are :
coefficient standard-error t-ratio
beta 0 -0.48340960E+05 0.22056912E+06 -0.21916467E+00
beta 1 0.94463413E+03 0.27249675E+03 0.34665887E+01
beta 2 0.40992561E+05 0.24716961E+05 0.16584790E+01
beta 3 0.50795307E+00 0.28266396E-01 0.17970210E+02
sigma-squared 0.79023831E+13
log likelihood function = -0.53013658E+04
the estimates after the grid search were :
beta 0 0.45823860E+06
beta 1 0.94463413E+03
beta 2 0.40992561E+05
beta 3 0.50795307E+00
sigma-squared 0.80620442E+13
gamma 0.50000000E-01
mu is restricted to be zero
eta is restricted to be zero
iteration = 0 func evals = 20 llf = -0.53016286E+04
0.45823860E+06 0.94463413E+03 0.40992561E+05 0.50795307E+00 0.80620442E+13
0.50000000E-01
gradient step
iteration = 5 func evals = 93 llf = -0.53016078E+04
0.45823854E+06 0.92882359E+03 0.40992200E+05 0.50782773E+00 0.80620442E+13
0.43096593E-01
search failed. loc of min limited by rounding
iteration = 6 func evals = 97 llf = -0.53016078E+04
0.45823854E+06 0.92882359E+03 0.40992200E+05 0.50782773E+00 0.80620442E+13
0.43096593E-01
the final mle estimates are :
coefficient standard-error t-ratio
beta 0 0.45823854E+06 0.13148648E+01 0.34850620E+06
beta 1 0.92882359E+03 0.22673456E+03 0.40965241E+01
beta 2 0.40992200E+05 0.52766433E+01 0.77686131E+04
beta 3 0.50782773E+00 0.17602053E-01 0.28850483E+02
sigma-squared 0.80620442E+13 0.10000000E+01 0.80620442E+13
gamma 0.43096593E-01 0.24647158E-01 0.17485421E+01
mu is restricted to be zero
eta is restricted to be zero
log likelihood function = -0.53016078E+04
the likelihood value is less than that obtained
using ols! - try again using different starting values
number of iterations = 6
(maximum number of iterations set at : 100)
number of cross-sections = 326
number of time periods = 1
total number of observations = 326
thus there are: 0 obsns not in the panel