y               ETA (Y/N) [OR NUMBER OF TE EFFECTS REGRESSORS (Zs)]
这里是问你zs的个数（因为你是用的模型2，是一步法）

那这个参数该怎么设置呢

影响因子的个数呀，是阿拉伯数字，你的影响因子有几个就填那数字呀。

那不就是自变量个数吗

模型2是一步法，你看看一步法里面除了有自变量的个数以外，还有一个是Z变量个数，就是影响效率的自变量个数。

z变量个数从哪儿可知？？？

这个要问你自己呀，谁也不能给你做主呀！

比如 全要素生产率受许多因素影响，贸易结构，能源结构，产业结构，市场等许多方面影响，如果你还没有想好这些Z变量，那你应该是用模型1呀，模型1是二步法，你是连基本知识没有搞懂在瞎问题哦。

实在对不起了，完全对牛弹琴哦。

你这一说我懂了，呵呵，谢谢你

那就好。

你好，除了那个英文说明，还有什么好一点的介绍随即前沿模型的书吗

一些国外的论文，中国的某些论文也有介绍呀。自己找找吧

你能帮我看看我分析的结果吗？？the final mle estimates are :

                 coefficient     standard-error    t-ratio

  beta 0         0.60409708E+00  0.78241856E-01  0.77208940E+01
  beta 1         0.58871309E+00  0.17616122E-01  0.33418995E+02
  beta 2         0.31781766E+00  0.42441773E-01  0.74883219E+01
  delta 0        0.17707213E+00  0.40230859E-01  0.44014007E+01
  delta 1       -0.30454618E-01  0.49261471E-02 -0.61822389E+01
  sigma-squared  0.10312160E-01  0.27750942E-02  0.37159676E+01
  gamma          0.19975467E+00  0.64746909E-01  0.30851615E+01

log likelihood function =   0.18390413E+03

LR test of the one-sided error =   0.22943081E+02
这里面的delta0和delta1怎么解释

是不是数据的事啊，我第一次输的时候，因为有十几个负数，所以出不来结果，对了，我用的是生产函数

对不起，我很久没有看这个了，目前一下子想不起来了，不过我毕业论文马上要用这方法，要过几天我才看书想起这些。

英文说明里有一个后缀为SHA的文件，里面貌似要写算法，但是我解压的文件里没有这个后缀的文件，是因为这个所以算不出结果的么？

是INS文件

楼主问题解决了么？

这样的回复好像一点都不解决问题……

但我确实是这样解决问题的。你要想自己不付出就有收获，那你永远无法进步！

英文说明大家都有仔细看过吧，既然你已经解决了，能不能请您详细说明一下是哪个环节可能存在问题所以frontier不出来结果？我现在是跑自带例子也没有结果，多谢

大神大神，一定帮我看看，坐等回复！！！！跪谢了…………我自己检查了无数遍了还是没有结果。
引导文件：
1               1=ERROR COMPONENTS MODEL, 2=TE EFFECTS MODEL
s1-dta.txt       DATA FILE NAME
b8-out.txt         OUTPUT FILE NAME
2               1=PRODUCTION FUNCTION, 2=COST FUNCTION
y               LOGGED DEPENDENT VARIABLE (Y/N)
31              NUMBER OF CROSS-SECTIONS
12               NUMBER OF TIME PERIODS
372              NUMBER OF OBSERVATIONS IN TOTAL
4             NUMBER OF REGRESSOR VARIABLES (Xs)
y               MU (Y/N) [OR DELTA0 (Y/N) IF USING TE EFFECTS MODEL]
y               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.
数据文件：在附件里面   谢谢谢谢

你要不留你Q，我加你Q，在个人平台留

怎么做的？求指导

我今天整整运行了一天运行出来了，仔细检查，按下面的文章多看几遍！！

[肖老师好！此文件英文部分为程序作者的说明，但有些操作方面没有具体详述，方括号中我为您加入了注释内容，具体的程序我调试成功了，结果也可行－by key]
FRONTIER Version 4.1
********************
A STOCHASTIIC FRONTIER ANALYSIS PROGRAM
[即sfa分析模型，计量统计软件]
by
Tim Coelli[作者信息，遇到具体的问题可与之联系]
Centre for Efficiency and Productivity Analysis
School of Economics
University of Queensland
Brisbane, QLD 4072
Australia.
email: t.coelli@economics.uq.edu.au
Web: http://www.uq.edu.au/economics/cepa/
[本软件实际下载地址：http://www.uq.edu.au/economics/cepa/frontier.htm ,如无法下载请留言索取]

GETTING STARTED:[即将文件复制到文件夹中或由压缩包解压到自己的文件夹中，不用详看]
1. Open the WINDOWS EXPLORER program on your PC.
2. Create a new folder on your hard drive, for example called FRONTIER, by
using the File/New/Folder option.
3. Copy ALL the files associated with FRONTIER into this folder, using
the File/Copy option or by "drag-and-drop".
4. If the files are stored in a FRONT41.ZIP file, you will then need
to unzip (extract) the files by double-clicking on the zip file and
extracting the contents of the zip file into the FRONTIER folder.

FILES USED BY FRONTIER[数据文件的使用方法]
FRONTIER uses three text files when it conducts an analysis. These are:
- a data file (eg. named eg1-dta.txt) [等处理“数据文件”]
- an instruction file (eg. named eg1-ins.txt)[“指令文件”]
- an output file (eg. named eg1-out.txt)[“输出文件”]
All of these files are text files. They can be edited using many programs.
For example, NOTEPAD, WORDPAD, WORD, WORD PERFECT, etc.
We suggest you use WORDPAD to view and edit these files.
[数据文件都是用“记事本”格式，方便编辑]
HOW TO RUN THE PROGRAM [具体程序运行步骤]
To practice running FRONTIER double-click on the FRONT41.EXE file name.
[双击FRONT41.EXE直接运行，但建议在DOS界面运行便于查看结果(不然后面会一闪界面就没了)，具体当面说明]
[注意一定要包含此四个文件：front41.exe,front41.FOR,front41.000,F77L3.EER]
The program will then ask for an instruction file name. Type in
eg1-ins.txt
(and hit the RETURN key). FRONTIER will only take a few seconds to complete
this small example. To look at the output file (eg1-out.txt) you then
simply double-click on the eg1-out.txt file name.
[根据提示，输入指示文件名，并回车。运行此范例后，可以双击eg1-out.txt查看结果]
[具体为：开始时出现如下提示：]
Do you wish to type instructions at the terminal (t)
or use an instruction file (f) ?
[即询问是手动输入命令（即一些输入参数）还是用一个指令文件（应事先把参数都写好放在指令文件中）]
[建议把“数据文件”放在同一目录后，写好参数到一个“指令文件”也放在同目录下]
[选择后者，即输入f,然后再输入指令文件名，回车即可打开“输出文件”查看结果]
[后面讲述一些应用技巧，粗略了解一下即可]
FILE NAMES IN DOS [在DOS界面的文件名规范，即命令操作注意事项，基本简短即可]
FRONTIER is a DOS computer program. In DOS all file names must satisfy certain
restrictions:
- no more than 12 characters
- no more than 3 characters after the period (".")
- no more than 8 characters before the period
That is, the largest possible file name has the form:
XXXXXXXX.XXX
Since we use text files, the file name will always have "txt" after the
period. That is:
XXXXXXXX.txt
[后缀用txt，便于双击直接查看]
CREATING A NEW INSTRUCTION FILE [指令文件的建立]
The easiest way to create a new instruction/command file is to open
an existing instruction file (eg. eg1-ins.txt) using WORDPAD and then save
it under a new name (eg. abc2-ins.txt). This is done by using the File/SaveAs
options in WORDPAD. Then you can edit the contents of this new file to suit
your new analysis.

CREATING DATA FILES USING EXCEL[用excel建立数据文件]
Many people store their data in Excel files. To construct a text file from
an Excel file, open the file in Excel and then use the File/SaveAs option in
Excel and save it as a text file. However, be sure to remove any column names
first - the data file should only contain numbers.
[即打开原excel文件后，另存为“文本文档”类型的文件即可]

MANUAL[指导手册]
Coelli, T. (1996) 'A Guide to FRONTIER Version 4.1: A Computer
Program for Stochastic Frontier Production and Cost Function
Estimation', CEPA Working Paper 96/08, University of New England.
A COPY OF THIS GUIDE IS PROVIDED IN THE FILE: FRONT41.PDF.
For additional information on these methods see Chapters 8 and 9 in Coelli,
Rao and Battese (1998), An Introduction to Efficiency and Productivity Analysis,
Kluwer Academic Publishers, Boston.

LIABILITY [权责说明]
Every effort has been made to ensure that this software is free of errors.
However, the software is supplied without any warranty as to the
performance or fitness of the program for any particular purpose. All
risk relating to the results and performance of this program is assumed by
the user. CEPA shall not be liable for any damages resulting from the
use of this product.
＝＝＝另附我整理的PDF中部分帮助文档解释，所述的特定文件名有所不同，彩色部分暂时无法显示＝＝＝＝＝
。。。略。。。
3.1 Files Needed[文件要求，这个在说明文档里有]
The execution of FRONTIER Version 4.1 on an IBM PC generally involves five files:
1) The executable file FRONT41.EXE
2) The start-up file FRONT41.000
3) A data file (for example, called TEST.DTA)
4) An instruction file (for example, called TEST.INS)
5) An output file (for example, called TEST.OUT).
The start-up file, FRONT41.000, contains values for a number of key variables such as the convergence criterion, printing flags and so on. This text file may be edited if the user wishes to alter any values. This file is discussed further in Appendix A. The data and instruction files must be created by the user prior to execution. The output file is created by FRONTIER during execution. Examples of a data, instruction and output files are listed in Section 4.
The program requires that the data be listed in an text file and is quite particular about the format.[程序的格式要求] The data must be listed by observation. There must be 3+k[+p] columns[列] presented in the following order:
1) Firm number (an integer in the range 1 to N)
2) Period number (an integer in the range 1 to T)
3) Yit
4) x1it
:
3+k) xkit
[3+k+1) z1it
:
3+k+p) zpit].
The z entries are listed in square brackets[方括号中的z] to indicate that they are not always needed. They are only used when Model 2 is being estimated. The observations can be listed in any order but the columns must be in the stated order[行间可换，列序要一致]. There must be at least one observation on each of the N firms and there must be at least one observation in time period 1 and in time period T. If you are using a single cross-section of data, then column 2 (the time period column) should contain the value “1” throughout.[单个cross-section数据，第二列都置1，如例中所示] Note that the data must be suitably transformed if a functional form other than a linear function is required[要把原始数据转换成本程序规范的函数形式]. The Cobb-Douglas and Translog functional forms are the most often used functional forms in stochastic frontier analyses. Examples involving these two forms will be provided in Section 4.[例子中用到了两个常用的形式]
The program can receive instructions either from a file or from a terminal. After typing “FRONT41” to begin execution, the user is asked whether instructions will come from a file or the terminal. The structure of the instruction file is listed in the next section. If the interactive (terminal) option is selected, questions will be asked in the same order as they appear in the instruction file. [程序提供了两种指令输入形式]：即询问是手动输入命令（即一些输入参数）还是用一个指令文件（应事先把参数都写好放在指令文件中）]
。。。。。。。
4. A FEW SHORT EXAMPLES[这里开始举例说明]
The best way to describe how to use the program is to provide some examples. In this section we shall consider the estimation of:
1) A Cobb-Douglas production frontier using cross-sectional data and assuming a half-normal distribution.
2) A Translog production frontier using cross-sectional data and assuming a truncated normal distribution.
3) A Cobb-Douglas cost frontier using cross-sectional data and assuming a half-normal distribution.
4) The Battese and Coelli (1992) specification (Model 1).
5) The Battese and Coelli (1995) specification (Model 2).
To keep the examples brief, we shall assume two production inputs in all cases. In the cross-sectional examples we shall have 60 firms, while in the panel data examples 15 firms and 4 time periods will be used.[以两个不同公司数的数据为例]
4.1 A Cobb-Douglas production frontier using cross-sectional data and assuming a half-normal distribution.
In this first example we wish to estimate the Cobb-Douglas production frontier:（以下公式输出不全，直接查看原文档）
(7) ln(Qi) = ?0 + ?1ln(Ki) + ?2ln(Li) + (Vi - Ui),
where Qi, Ki and Li are output, capital and labour, respectively, and Vi and Ui are assumed normal and half-normal distributed, respectively. The text file EG1.DAT contains 60 observations on firm-id, time-period, Q, K and L, in that order (refer to Table 1a). Note that the time-period column contains only 1’s because this is cross-sectional data. To estimate (7) we first must construct a data file which contains the logs of the the inputs and output. This can be done using any number of computer packages. The SHAZAM program (see White, 1993) has been used in this document. The SHAZAM instruction file EG1.SHA (refer Table 1b) reads in data from EG1.DAT, obtains the logs of the relevant variables and writes these out to the file EG1.DTA (refer Table 1c). This file has a similar format to the original data file, except that the inputs and output have been logged.
We then create an instruction file[讲述指令文件的使用] for the FRONTIER program (named EG1.INS) by first making a copy of the BLANK.INS file[可以根据这个文件（具体可能不是这个名字，找指令文件即可）中的提示进行修改，然后改好文件名] which is supplied with the program. We then edit this file (using a text editor such as DOS EDIT) and type in the relevent information. The EG1.INS file is listed in Table 1d. The purpose of the majority of entries in the file should be self explanatory, due to the comments on the right-hand side of the file. The first line[第一行选择模式，后续开始解释每一行] allows you to indicate whether Model 1 or 2 is required. Because of the simple form of the model this first example (and the next two examples) it does not matter whether “1” or “2” is entered. On the next two lines of the file the name of the data file (EG1.DTA) and an output file name (here we have used EG1.OUT) are specified. On line 4 a “1” is entered to indicate we are estimating a production function, and on line 5 a “y” is entered to indicate that the dependent variable has been logged (this is used by the program to select the correct formula for efficiency estimates). Then on the next four lines we specify the number of firms (60); time periods (1); total number of observations (60) and number of regressors (2). On the next three lines we have answered no (n) to each question. We have said no to ? because we are assuming the half normal distribution. We have answered no to ? because we have only one cross-section of data and hence cannot consider time-varying efficiencies. Lastly, we have answered no to specifying starting values because we wish them to be selected using a grid search.
[具体运行的说明，参见上面的帮助]Finally we type FRONT41 at the DOS prompt, select the instruction file option (f) and then type in the name of the instruction file (EG1.INS). The program will then take somewhere between a few seconds and a few minutes to estimate the frontier model and send the output to the file you have named (EG1.OUT). This file is reproduced in Table 1e.



我的问题出在了文件名字，在DOS运行时一定要加后缀.txt

应该还是数据的问题

大神，一定帮我看看，同学的数据都能出结果，为啥我的数据就不能，只是换了个数据，为什么就没结果了，拜托拜托
2             1=ERROR COMPONENTS MODEL, 2=TE EFFECTS MODEL
eg2.dta         DATA FILE NAME
eg2.out         OUTPUT FILE NAME
1               1=PRODUCTION FUNCTION, 2=COST FUNCTION
y               LOGGED DEPENDENT VARIABLE (Y/N)
6            NUMBER OF CROSS-SECTIONS
8              NUMBER OF TIME PERIODS
48              NUMBER OF OBSERVATIONS IN TOTAL
5              NUMBER OF REGRESSOR VARIABLES (Xs)
y               MU (Y/N) [OR DELTA0 (Y/N) IF USING TE EFFECTS MODEL]
2               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
                                                      DELTAK]

                                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.


数据：
       N              T              LY             LX1            LX2     &
       LX1S           LX2S           LX12           Z1             Z2
    1.000000       1.000000       7.536407      0.7466879       2.091864
   0.5575429       4.375895       1.561970       215.9300       111.2100
    2.000000       1.000000       8.487198      0.9202828       1.945910
   0.8469203       3.786566       1.790788       70.51000       88.78000
    3.000000       1.000000       9.500923      0.5306283       2.397895
   0.2815663       5.749902       1.272391       146.3900       59.86000
    4.000000       1.000000       7.271148      0.9202828       1.757858
   0.8469203       3.090064       1.617726       125.4500       5.460000
    5.000000       1.000000       9.561280       1.196948       2.261763
    1.432685       5.115572       2.707213       83.70000       253.6500
    6.000000       1.000000       5.719951      0.2776317      0.4054651
   0.7707938E-01  0.1644020      0.1125700       190.7400       138.3300
    7.000000       2.000000       7.511355      0.7466879       2.116256
   0.5575429       4.478537       1.580182       273.1300       133.2700
    8.000000       2.000000       8.486284      0.9321641       1.974081
   0.8689299       3.896996       1.840167       81.54000       88.65000
    9.000000       2.000000       9.508696      0.5423243       2.406945
   0.2941156       5.793385       1.305345       163.1700       87.44000
    10.00000       2.000000       7.259630      0.9360934       1.774952
   0.8762708       3.150456       1.661521       129.2400      -2.400000
    11.00000       2.000000       9.511433       1.226712       2.261763
    1.504823       5.115572       2.774533       116.3000       215.0600
    12.00000       2.000000       5.760919      0.3293037      0.4700036
   0.1084410      0.2209034      0.1547740       219.0300       294.2900
    13.00000       3.000000       7.512426      0.7323679       2.104134
   0.5363627       4.427381       1.541000       302.7700       169.3900
    14.00000       3.000000       8.484331      0.9282193       1.987874
   0.8615911       3.951644       1.845183       78.82000       93.07000
    15.00000       3.000000       9.497640      0.5596158       2.341806
   0.3131698       5.484054       1.310512       153.4200       50.84000
    16.00000       3.000000       7.220235      0.9669838       2.066863
   0.9350578       4.271922       1.998623       117.8600       21.63000
    17.00000       3.000000       9.466510       1.241269       2.028148
    1.540748       4.113385       2.517477       61.15000       240.5400
    18.00000       3.000000       5.989162      0.3364722      0.6418539
   0.1132136      0.4119764      0.2159660       218.1200       340.0700
    19.00000       4.000000       7.528466      0.7514161       2.128232
   0.5646261       4.529370       1.599188       340.1200       186.8000
    20.00000       4.000000       8.459947      0.9895412       2.014903
   0.9791918       4.059834       1.993830       91.98000       64.11000

请问如果使用SFA方法，各个公司的时间段不同可以吗

ETA那里选 Y或N而不是数字

直观来讲，你5个自变量外加2个影响因素，只有48个数据。。。很难算出结果啊。。。

个人观点，未必对，但是数据愈多才越准确吧

因为第一行选择了2，所以是一步法模型，命令文件的这一行变成了“请问有多少个影响因素”

所以，他这里写2，是对的，如果写Y就错了。