[求助]Stochastic Frontier Model in STATA

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

<P>有没有人懂STATA中的Stochastic Frontier Regression 中估计的technical inefficiency是什么含义？是回归方程中的残差还是the ratio of actual number and potential number? </P>
<P>或者谁有stata的manual，小弟谢过先！</P>[em08][em08]

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏7 回帖

关键词：Stochastic frontier Stochast frontie model potential technical number manual actual

Stata help for xtfrontier

 help xtfrontier dialog: xtfrontier also see: xtfrontier postestimation ------------------------------------------------------------------------------- 
 Title 
 [XT] xtfrontier -- Stochastic frontier models for panel data 
 
 Syntax 
 Time-invariant model 
 xtfrontier depvar [indepvars] [if] [in] [weight] , ti [ti_options] 
 
 Time-varying decay model 
 xtfrontier depvar [indepvars] [if] [in] [weight] , tvd [tvd_options] 
 
 ti_options description ------------------------------------------------------------------------- Model i(varname_i) use varname_i as the panel ID variable noconstant suppress constant term ti use time-invariant model; the default cost fit cost frontier model constraints(constraints) apply specified linear constraints 
 SE vce(vcetype) vcetype may be bootstrap or jackknife 
 Reporting level(#) set confidence level; default is level(95) 
 Max options ml_maximize_options control the maximization process; seldom used ------------------------------------------------------------------------- 
 tvd_options description ------------------------------------------------------------------------- Model i(varname_i) use varname_i as the panel ID variable t(varname_t) use varname_t as the time variable noconstant suppress constant term tvd use time-varying decay model cost fit cost frontier model constraints(constraints) apply specified linear constraints 
 SE vce(vcetype) vcetype may be bootstrap or jackknife 
 Reporting level(#) set confidence level; default is level(95) 
 Max options ml_maximize_options control the maximization process; seldom used ------------------------------------------------------------------------- 
 You must tsset your data before using xtfrontier; see tsset. depvars and indepvars may contain time-series operators; see tsvarlist. fweights and i weights are allowed; see weight. bootstrap, by, jackknife, statsby, and xi may be used with xtfrontier; see prefix. See xtfrontier postestimation for features available after estimation. 
 
 Description 
 xtfrontier fits stochastic production or cost frontier models for panel data. More precisely, xtfrontier estimates the parameters of a linear model with a disturbance generated by specific mixture distributions. 
 The disturbance term in a stochastic frontier model is assumed to have two components. One component is assumed to have a strictly non-negative distribution, and the other component is assumed to have a symmetric distribution. In the econometrics literature, the non-negative component is often referred to as the inefficiency term, and the component with the symmetric distribution as the idiosyncratic error. xtfrontier permits two different parameterizations of the inefficiency term: a time-invariant model and the Battese-Coelli parameterization of time-effects. In the time-invariant model, the inefficiency term assumed to have a truncated-normal distribution. In the Battese-Coelli parameterization of time effects, the inefficiency term is modeled as a truncated-normal random variable multiplied by a specific function of time. In both models, the idiosyncratic error term is assumed to have a normal distribution. The only panel-specific effect is the random inefficiency term. 
 
 Options for time-invariant model 
 +-------+ ----+ Model +------------------------------------------------------------ 
 i(varname_i); see estimation options. 
 ti specifies that the parameters of the time-invariant technical inefficiency model be estimated. 
 noconstant; see estimation options. 
 cost specifies the frontier model be fitted in terms of a cost function instead of a production function. By default, xtfrontier fits a production frontier model. 
 constraints(constraints); see estimation options. 
 +----+ ----+ SE +--------------------------------------------------------------- 
 vce(vcetype); see vce_option. 
 +-----------+ ----+ Reporting +-------------------------------------------------------- 
 level(#); see estimation options. 
 +-------------+ ----+ Max options +------------------------------------------------------ 
 ml_maximize_options: difficult, technique(algorithm_spec), iterate(#), [no]log, trace, gradient, showstep, hessian, shownrtolerance, tolerance(#), ltolerance(#), gtolerance(#), nrtolerance(#), nonrtolerance, from(init_specs); see ml and maximize. These options are seldom used. 
 
 Options for time-varying decay model 
 +-------+ ----+ Model +------------------------------------------------------------ 
 i(varname_i), t(varname_t); see estimation options. 
 noconstant; see estimation options. 
 tvd specifies that the parameters of the time-varying decay model be estimated. 
 cost specifies the frontier model be fitted in terms of a cost function instead of a production function. By default, xtfrontier fits a production frontier model. 
 constraints(constraints); see estimation options. 
 +----+ ----+ SE +--------------------------------------------------------------- 
 vce(vcetype); see vce_option. 
 +-----------+ ----+ Reporting +-------------------------------------------------------- 
 level(#); see estimation options. 
 +-------------+ ----+ Max options +------------------------------------------------------ 
 ml_maximize_options: difficult, technique(algorithm_spec), iterate(#), [no]log, trace, hessian, gradient, showstep, shownrtolerance, tolerance(#), ltolerance(#), gtolerance(#), nrtolerance(#), nonrtolerance, from(init_specs); see ml and maximize. These options are seldom used. 
 
 Examples 
 . xtfrontier lnv lnk lnl, i(id) t(t) tvd 
 . xtfrontier lnv lnk lnl, i(id) ti 
 . xtfrontier lnv lnk lnl, i(id) t(t) tvd cost 
 
 Also see 
 Manual: [XT] xtfrontier 
 Online: xtfrontier postestimation; frontier, regress, tsset, xtreg 

是回归方程中的non-negative residual

SFA中的殘差是被用來估計『技術進步』的用途。但由于一般殘差會是不偏的常態分配狀態，SFA將其殘差改成以U-V的形式出現。U為效率邊界，V則為技術無效率。

就這樣了

。。。。。。。。

niiiiiiiiiiiiice

这个问题我正在研究，郁闷

. xtset id year
       panel variable:  id (unbalanced)
        time variable:  year, 2001 to 2014
                delta:  1 unit

. xtfrontier lnTC lny1 lny2 lny3 lnw1 lnw2 lnw3 lnE,i(id) t(year) tvd

Iteration 0:   log likelihood =   9.645561  (not concave)
Iteration 1:   log likelihood =  22.959616  (not concave)
Iteration 2:   log likelihood =  23.702739  
Iteration 3:   log likelihood =    25.5583  (not concave)
Iteration 4:   log likelihood =  26.750376  
Iteration 5:   log likelihood =   28.05029  
Iteration 6:   log likelihood =  28.831103  (not concave)
Iteration 7:   log likelihood =  29.023985  (not concave)
Iteration 8:   log likelihood =  29.232894  
Iteration 9:   log likelihood =  29.490194  
Iteration 10:  log likelihood =  29.544716  
Iteration 11:  log likelihood =  29.690238  (not concave)
Iteration 12:  log likelihood =  29.752345  
Iteration 13:  log likelihood =  29.837107  
Iteration 14:  log likelihood =  29.877669  
Iteration 15:  log likelihood =  29.942216  
Iteration 16:  log likelihood =  29.972518  
Iteration 17:  log likelihood =  30.001828  
Iteration 18:  log likelihood =  30.018416  
Iteration 19:  log likelihood =  30.033189  
Iteration 20:  log likelihood =  30.041614  
Iteration 21:  log likelihood =  30.054199  
Iteration 22:  log likelihood =  30.061482  
Iteration 23:  log likelihood =  30.066727  
Iteration 24:  log likelihood =  30.073757  
Iteration 25:  log likelihood =  30.075289  
为什么我做出来的结果是这样，得不出结果，求指导

Stochastic frontier model的原理有谁能解释一下？