我做的一个FRONTIER练习

我做的一个练习：

第一步：在Excel中录入原始数据，并生成对数数据。在对数数据前加上两列：第1列为序号列；第二列为时期列，我用的是截面数据，只有一个时期。若用面板数据，则第二组中的30个数据，序号仍为1-30，时期变为2;第三组等，类推。将Excel中的序号、时期号、对数数据一并复制，粘贴到新建的记事本文档中，保存为av3x1995.DTA（文件名按自己易记的符号进行定义，我取名为av3x1995.DAT，但后缀.DAT一定要有，否则会默认保存为.txt格式，影响以后程序的读取。另：粘贴之后，行列要调整整齐。）

av3x1995.DTA的内容如下：

1 1 -1.523792196 0.371029625 -2.849128799 -1.594076627 2 1 -1.827913354 0.406310536 -3.36983641 -1.478058538 3 1 -2.107239544 0.070799819 -2.907195658 -0.856598402 4 1 -2.237894932 0.123203703 -2.746638835 -0.644119346 5 1 -2.40805324 -0.677175433 -3.498931122 -1.261555166 6 1 -1.306422501 -0.168724436 -2.457539108 -0.708212748 7 1 -1.461163139 -0.31291294 -2.190172984 -0.520529044 8 1 -1.3397812 0.113358047 -2.307805602 -0.824032948 9 1 -1.30420055 -0.506317206 -2.535157735 -1.478342575 10 1 -1.669642276 -0.542940218 -2.571861103 -0.91096939 11 1 -1.313434765 0.145840803 -2.677855299 -0.213762044 12 1 -1.945069917 -0.468675133 -2.669336983 -0.418588994 13 1 -1.050645135 -0.212390046 -2.19487816 -0.186709172 14 1 -1.939305096 -1.04194166 -2.819476139 -0.524592346 15 1 -1.76919911 -0.149140908 -2.554834466 -0.62238144 16 1 -1.980523649 -0.260926201 -2.529866564 -0.36481127 17 1 -1.637157108 -0.616080539 -2.253409566 -0.492175507 18 1 -1.788784572 -0.558916406 -2.770203509 -0.236903836 19 1 -0.878061138 0.114949548 -2.028806934 -0.103249968 20 1 -1.531944521 -0.313997267 -2.483074215 0.059853117 21 1 -0.736390072 -0.025800646 -2.345578139 -0.092766353 22 1 -1.494214545 -0.596852684 -2.471133177 0.317003705 23 1 -1.422654184 -0.479095645 -2.309305879 0.800474394 24 1 -1.817589571 -0.316685296 -2.653562016 0.266846512 25 1 -2.356344189 -1.019186675 -4.682748321 -0.624606807 26 1 -2.10478899 -0.540490153 -2.481926022 -0.244546339 27 1 -1.975188423 -0.176623536 -2.86416359 -0.290487123 28 1 -2.017561552 0.061254794 -3.306041036 -0.296557591 29 1 -2.442083132 -0.141470806 -2.831058945 -0.7054439 30 1 -2.750338015 -1.447404712 -3.713644012 -2.282641412

第二步：新建一个用于记录输出的空白的记事本文件。我取名为av3x1995.OUT

第三步：编辑*.INS文件，编辑后，我另存为av3x1995.INS(同上，文件名后缀.INS不能省略。程序自带的.INS文件，可用记事本打开，修改它，然后另存为一个你想要的名字即可）。编辑后的内容如下。

1 1=ERROR COMPONENTS MODEL, 2=TE EFFECTS MODEL av3x.dta DATA FILE NAME av3x.out OUTPUT FILE NAME

1 1=PRODUCTION FUNCTION, 2=COST FUNCTION y LOGGED DEPENDENT VARIABLE (Y/N) 30 NUMBER OF CROSS-SECTIONS 1 NUMBER OF TIME PERIODS

30 NUMBER OF OBSERVATIONS IN TOTAL 3 NUMBER OF REGRESSOR VARIABLES (Xs)

y 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.

第四步：双击front41.exe,出现dos界面，并了出现提示句:Do you wish to type instructions at the terminal or use an instruction file? 此时键入f,然后回车。出现提示行：enter instruction file name: 我在此处键入文件名，av3x1995.INS，然后回车。按回车键之后，dos界面消失。找到前面建立的av3x1995.OUT文档，打开它，结果如下：

Output from the program FRONTIER (Version 4.1c)

instruction file = av3x1995.INS data file = av3x1995.dta

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 -0.24797236E+00 0.34909410E+00 -0.71033100E+00 beta 1 0.24095601E+00 0.16016092E+00 0.15044620E+01 beta 2 0.50002310E+00 0.13947141E+00 0.35851298E+01 beta 3 0.87698820E-01 0.11305364E+00 0.77572755E+00 sigma-squared 0.11425214E+00

log likelihood function = -0.78814296E+01 the estimates after the grid search were : beta 0 -0.16162288E+00 beta 1 0.24095601E+00 beta 2 0.50002310E+00 beta 3 0.87698820E-01 sigma-squared 0.10647475E+00 gamma 0.11000000E+00 mu 0.00000000E+00 eta is restricted to be zero

iteration = 0 func evals = 20 llf = -0.78811951E+01

-0.16162288E+00 0.24095601E+00 0.50002310E+00 0.87698820E-01 0.10647475E+00 0.11000000E+00 0.00000000E+00 gradient step

iteration = 5 func evals = 49 llf = -0.78811676E+01

-0.16257650E+00 0.24198088E+00 0.49935920E+00 0.87908832E-01 0.10649298E+00 0.11047577E+00 0.66877603E-03

iteration = 10 func evals = 146 llf = -0.78809863E+01

-0.12049695E+00 0.24264263E+00 0.49967035E+00 0.87839857E-01 0.10734169E+00 0.14844887E+00 0.64194228E-01

iteration = 15 func evals = 264 llf = -0.78807786E+01

-0.72525430E-01 0.24399490E+00 0.49862348E+00 0.88270824E-01 0.10746730E+00 0.19727127E+00 0.13097261E+00

iteration = 20 func evals = 384 llf = -0.78804758E+01

-0.60453103E-01 0.24276008E+00 0.49977743E+00 0.87985980E-01 0.10408756E+00 0.16669544E+00 0.15959356E+00

iteration = 25 func evals = 512 llf = -0.78798764E+01

-0.69635321E-02 0.24314039E+00 0.49880267E+00 0.88350490E-01 0.10322546E+00 0.19403870E+00 0.22732353E+00

iteration = 30 func evals = 620 llf = -0.78792024E+01

0.86807823E-01 0.24452966E+00 0.49407760E+00 0.89925967E-01 0.10274898E+00 0.28455866E+00 0.33890952E+00

iteration = 35 func evals = 643 llf = -0.78791212E+01

0.85726671E-01 0.24445656E+00 0.49457135E+00 0.89810902E-01 0.10281607E+00 0.28687487E+00 0.33639150E+00

iteration = 40 func evals = 662 llf = -0.78790605E+01

0.84886081E-01 0.24436726E+00 0.49511826E+00 0.89669198E-01 0.10289965E+00 0.28619365E+00 0.33351891E+00

iteration = 45 func evals = 683 llf = -0.78790536E+01

0.83711905E-01 0.24431336E+00 0.49541997E+00 0.89583213E-01 0.10294836E+00 0.28513877E+00 0.33142686E+00

iteration = 50 func evals = 707 llf = -0.78790531E+01

0.84242510E-01 0.24433115E+00 0.49532681E+00 0.89611670E-01 0.10293269E+00 0.28563188E+00 0.33228227E+00

iteration = 54 func evals = 719 llf = -0.78790531E+01

0.84202824E-01 0.24432989E+00 0.49533327E+00 0.89609658E-01 0.10293379E+00 0.28559435E+00 0.33220821E+00

the final mle estimates are :

coefficient standard-error t-ratio

beta 0 0.84202824E-01 0.12899318E+01 0.65276960E-01 beta 1 0.24432989E+00 0.11729117E+00 0.20831055E+01 beta 2 0.49533327E+00 0.41596028E+00 0.11908187E+01 beta 3 0.89609658E-01 0.14687123E+00 0.61012398E+00 sigma-squared 0.10293379E+00 0.12595232E+00 0.81724406E+00 gamma 0.28559435E+00 0.62586937E+01 0.45631623E-01 mu 0.33220821E+00 0.36397807E+01 0.91271491E-01 eta is restricted to be zero

log likelihood function = -0.78790531E+01 LR test of the one-sided error = 0.47531031E-02 with number of restrictions = 2

[note that this statistic has a mixed chi-square distribution]

number of iterations = 54

(maximum number of iterations set at : 100) number of cross-sections = 30 number of time periods = 1 total number of observations = 30 thus there are: 0 obsns not in the panel

covariance matrix :

0.16639239E+01 -0.18458078E+01 0.72605602E+01 -0.31025345E+01 0.23568121E+01 -0.10753333E+03 -0.70321987E+01

-0.18458078E+01 0.13757220E-01 0.24586297E-01 -0.13055869E-01 0.13320234E-01 -0.16314784E+01 -0.20188444E+01

0.72605602E+01 0.24586297E-01 0.17302296E+00 0.44768681E-01 -0.45792319E-01 0.57190106E+01 0.71998453E+01

-0.31025345E+01 -0.13055869E-01 0.44768681E-01 0.21571157E-01 0.20655240E-01 -0.28064391E+01 -0.34109891E+01

0.23568121E+01 0.13320234E-01 -0.45792319E-01 0.20655240E-01 0.15863987E-01 0.27627916E+01 0.25311277E+01

-0.10753333E+03 -0.16314784E+01 0.57190106E+01 -0.28064391E+01 0.27627916E+01 0.39171247E+02 -0.14175791E+03

-0.70321987E+01 -0.20188444E+01 0.71998453E+01 -0.34109891E+01 0.25311277E+01 -0.14175791E+03 0.13248004E+02

technical efficiency estimates :

firm eff.-est.

1 0.75659631E+00 2 0.74444002E+00 3 0.65360797E+00 4 0.61033545E+00 5 0.69309967E+00 6 0.77049973E+00 7 0.72030522E+00 8 0.73974918E+00 9 0.80396327E+00 10 0.73391448E+00 11 0.76703971E+00 12 0.67905841E+00 13 0.78646180E+00 14 0.72259647E+00 15 0.69024613E+00 16 0.64935607E+00 17 0.70639911E+00 18 0.71923667E+00 19 0.78696275E+00 20 0.72458997E+00 21 0.83978206E+00 22 0.73932467E+00

23 0.72405630E+00 24 0.68302936E+00 25 0.81382618E+00 26 0.63297681E+00 27 0.67597131E+00 28 0.69841734E+00 29 0.59452181E+00 30 0.70139863E+00

mean efficiency = 0.71872543E+00

这里面就是我想要的东西。（当然，我不知道你想要什么）

23 0.72405630E+00 24 0.68302936E+00 25 0.81382618E+00 26 0.63297681E+00 27 0.67597131E+00 28 0.69841734E+00 29 0.59452181E+00 30 0.70139863E+00

mean efficiency = 0.71872543E+00

这里面就是我想要的东西。（当然，我不知道你想要什么）

本文来源：https://www.bwwdw.com/article/f90w.html