SFA的dta:
1 1 210811 807279 82351
2 1 700 135942 9810
3 1 95882 493820 32577
4 1 20098 185169 19201
5 1 932 125088 15759
6 1 51 12628 2670
7 1 1165 3077755 25639
8 1 22490 166287 19147
9 1 1394 76975 7502
10 1 32127 250956 16002
11 1 4913 49461 5047
12 1 1500 56541 6830
13 1 2713 187974 20047
14 1 117 68464 6117
15 1 3200 35202 6372
16 1 2170 38657 8263
17 1 700 39857 4784
18 1 1150 69749 4847
ins:
1 1=ERROR COMPONENTS MODEL, 2=TE EFFECTS MODEL
00.dta DATA FILE NAME
00.out OUTPUT FILE NAME
1 1=PRODUCTION FUNCTION, 2=COST FUNCTION
n LOGGED DEPENDENT VARIABLE (Y/N)
18 NUMBER OF CROSS-SECTIONS
1 NUMBER OF TIME PERIODS
18 NUMBER OF OBSERVATIONS IN TOTAL
2 NUMBER OF REGRESSOR VARIABLES (Xs)
n MU (Y/N) [OR DELTA0 (Y/N) IF USING TE EFFECTS MODEL]
n ETA (Y/N) [OR NUMBER OF TE EFFECTS REGRESSORS (Zs)]
n STARTING VALUES (Y/N)
IF YES THEN BETA0
BETA1 TO
BETAK
SIGMA SQUARED
GAMMA
MU [OR DELTA0
ETA DELTA1 TO
DELTAP]
NOTE: IF YOU ARE SUPPLYING STARTING VALUES
AND YOU HAVE RESTRICTED MU [OR DELTA0] TO BE
ZERO THEN YOU SHOULD NOT SUPPLY A STARTING
VALUE FOR THIS PARAMETER.
输出结果out:
Output from the program FRONTIER (Version 4.1c)
instruction file = 00.ins
data file = 00.dta
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 -0.19676212E+05 0.47452804E+04 -0.41464803E+01
beta 1 -0.16751105E-01 0.54632359E-02 -0.30661508E+01
beta 2 0.29175653E+01 0.21124485E+00 0.13811297E+02
sigma-squared 0.22032734E+09
log likelihood function = -0.19679562E+03
the estimates after the grid search were :
beta 0 -0.62188920E+04
beta 1 -0.16751105E-01
beta 2 0.29175653E+01
sigma-squared 0.36470558E+09
gamma 0.78000000E+00
mu is restricted to be zero
eta is restricted to be zero
iteration = 0 func evals = 20 llf = -0.19638101E+03
-0.62188920E+04-0.16751105E-01 0.29175653E+01 0.36470558E+09 0.78000000E+00
gradient step
iteration = 5 func evals = 73 llf = -0.19633578E+03
-0.62188921E+04-0.18026704E-01 0.29626649E+01 0.36470558E+09 0.80107148E+00
search failed. fn val indep of search direction
iteration = 6 func evals = 76 llf = -0.19633578E+03
-0.62188921E+04-0.18026704E-01 0.29626649E+01 0.36470558E+09 0.80107148E+00
the final mle estimates are :
coefficient standard-error t-ratio
beta 0 -0.62188921E+04 0.10044958E+01 -0.61910581E+04
beta 1 -0.18026704E-01 0.50336188E-02 -0.35812613E+01
beta 2 0.29626649E+01 0.16971774E+00 0.17456424E+02
sigma-squared 0.36470558E+09 0.10000000E+01 0.36470558E+09
gamma 0.80107148E+00 0.14127008E+00 0.56704966E+01
mu is restricted to be zero
eta is restricted to be zero
log likelihood function = -0.19633578E+03
LR test of the one-sided error = 0.91968867E+00
with number of restrictions = 1
[note that this statistic has a mixed chi-square distribution]
number of iterations = 6
(maximum number of iterations set at : 100)
number of cross-sections = 18
number of time periods = 1
total number of observations = 18
thus there are: 0 obsns not in the panel
covariance matrix :
0.10090119E+01 -0.55570968E-04 -0.89672496E-02 0.12205178E-14 0.33144948E-02
-0.55570968E-04 0.25337318E-04 -0.49057933E-03 0.76417518E-13 -0.10730319E-03
-0.89672496E-02 -0.49057933E-03 0.28804112E-01 0.59073831E-09 0.10773034E-01
0.12205178E-14 0.76417518E-13 0.59073831E-09 0.10000000E+01 0.69349074E-09
0.33144948E-02 -0.10730319E-03 0.10773034E-01 0.69349074E-09 0.19957234E-01
technical efficiency estimates :
firm eff.-est.
1 0.94905629E+00
2 0.20855760E+00
3 0.95922433E+00
4 0.53802360E+00
5 0.21842841E+00
6 -0.34492478E+01
7 0.17397356E+00
8 0.57610889E+00
9 0.18900275E+00
10 0.79249337E+00
11 0.10505023E+00
12 0.16413855E+00
13 0.24258198E+00
14 0.29769807E-01
15 0.21220643E+00
16 0.24848994E+00
17 -0.16395915E+00
18 -0.17438490E+00
mean efficiency = 0.10108411E+00
请帮我看看问题到底出在哪里了?