Sensitivity analysis of stochastic frontier analysis models
-
Kekoura Sakouvogui
,
Saleem Shaik
Abstract
The efficiency measures of the Stochastic Frontier Analysis (SFA) models are dependent on distributional assumptions of the one-sided error or inefficiency term. Given the intent of earlier researchers in the evaluation of a single inefficiency distribution using Monte Carlo (MC) simulation, much attention has not been paid to the comparative analysis of SFA models. Our paper aims to evaluate the effects of the assumption of the inefficiency distribution and thus compares different SFA model assumptions by conducting a MC simulation. In this paper, we derive the population statistical parameters of truncated normal, half-normal, and exponential inefficiency distributions of SFA models with the objective of having comparable sample mean and sample standard deviation during MC simulation. Thus, MC simulation is conducted to evaluate the statistical properties and robustness of the inefficiency distributions of SFA models and across three different misspecification scenarios, sample sizes, production functions, and input distributions. MC simulation results show that the misspecified truncated normal SFA model provides the smallest mean absolute deviation and mean square error when the true data generating process is a half-normal inefficiency distribution.
Acknowledgements
The views set forth are those of the authors and do not indicate concurrence by the United States Census Bureau nor the Department of Commerce.
References
[1] D. Aigner and S. Chu, On estimating the industry production function, Amer. Econ. Rev. 58 (1968), no. 4, 826–839. Suche in Google Scholar
[2] D. Aigner, C. Lovell and P. Schmidt, Formulation and estimation of stochastic frontier production function models, J. Econometrics 6 (1977), 21–37. 10.1016/0304-4076(77)90052-5Suche in Google Scholar
[3] M. Andor and F. Hesse, A Monte Carlo simulation comparing DEA, SFA and two simple approaches to combine efficiency estimates, CAWM Discussion Papers 51, Center of Applied Economic Research Munster, University of Münster, 2011. Suche in Google Scholar
[4] M. Andor and F. Hesse, The StoNED age: The departure into a new era of efficiency analysis? A monte carlo comparison of StoNED and the “oldies” (SFA and DEA), J. Productivity Anal. 41 (2014), 85–109. 10.1007/s11123-013-0354-ySuche in Google Scholar
[5] O. Badunenko, J. Henderson and C. Kumbhakar, When, where and how to perform efficiency estimation, J. R. Stat. Soc. 175 (2012), 863–892. 10.1111/j.1467-985X.2011.01023.xSuche in Google Scholar
[6] R. Banker, V. Gadh and W. Gorr, A Monte Carlo comparison of two production frontier estimation methods: Corrected ordinary least squares and data envelopment analysis, European J. Oper. Res. 67 (1993), no. 3, 332–343. 10.1016/0377-2217(93)90289-YSuche in Google Scholar
[7] E. Battese and J. Coelli, Frontier production functions, technical efficiency and panel data: With application to paddy fanners in India, J. Productivity Anal. 3 (1992), no. 1–2, 153–169. 10.1007/978-94-017-1923-0_10Suche in Google Scholar
[8] E. Bravo-Ureta and E. Pinheiro, Efficiency analysis of developing country agriculture: A review of the frontier function literature, Agricultural Res. Econ. Rev. 22 (1993), 88–101. 10.1017/S1068280500000320Suche in Google Scholar
[9] Y. Chen, P. Schmidt and H. Wang, Consistent estimation of the fixed effects stochastic frontier model, J. Econometrics 181 (2014), no. 2, 65–76. 10.1016/j.jeconom.2013.05.009Suche in Google Scholar
[10] W. Cobb and P. Douglas, Theory of production, Amer. Econ. Rev. 18 (1928), 139–165. Suche in Google Scholar
[11] J. Coelli, Recent developments in frontier modelling and efficiency measurement, Aust. J. Agricultural Res. Econ. 39 (1995), 219–245. 10.1111/j.1467-8489.1995.tb00552.xSuche in Google Scholar
[12] G. Debreu, The coefficient of resource utilization, Econometrica 19 (1951), 273–292. 10.1017/CCOL052123736X.002Suche in Google Scholar
[13] J. Farrell, The Measurement of productive efficiency, J. R. Stat. Soc. Ser. A 120 (1957), 253–290. 10.2307/2343100Suche in Google Scholar
[14] W. Greene, A gamma-distributed stochastic frontier model, J. Econometrics 46 (1990), 141–164. 10.1016/0304-4076(90)90052-USuche in Google Scholar
[15] W. Greene, Reconsidering heterogeneity and inefficiency: Stochastic frontier models, J. Econometrics 126 (2005), no. 2, 269–303. 10.1016/j.jeconom.2004.05.003Suche in Google Scholar
[16] G. Hildebrand and T. Liu, Manufacturing Production Functions in the United States, Cornell University, Ithaca, 1965. Suche in Google Scholar
[17] C. Horrace and C. Parmeter, A Laplace stochastic frontier model, Econometric Rev. 37 (2015), no. 3, 260–280. 10.1080/07474938.2015.1059715Suche in Google Scholar
[18] C. Huang and J. Lai, Estimation of stochastic frontier models based on multimodel inference, J. Productivity Anal. 38 (2012), no. 3, 273–284. 10.1007/s11123-011-0260-0Suche in Google Scholar
[19] U. Jensen, Misspecification preferred: the sensitivity of inefficiency rankings, J. Productivity Anal. 23 (2005), 223–244. 10.1007/s11123-005-1330-ySuche in Google Scholar
[20] J. Jondrow, I. Materov, K. Lovell and P. Schmidt, On the estimation of technical inefficiency in the stochastic frontier production function model, J. Econometrics 19 (1982), 233–238. 10.1016/0304-4076(82)90004-5Suche in Google Scholar
[21] G. Koop, J. Steel and J. Osiewalski, Posterior analysis of stochastic frontier models using Gibbs sampling, Comput. Statist. 10 (1995), 353–373. Suche in Google Scholar
[22] S. Kumbhakar, The specification of technical and allocative inefficiency in stochastic production and profit frontiers, J. Econometrics 34 (1987), 335–348. 10.1016/0304-4076(87)90016-9Suche in Google Scholar
[23] S. Kumbhakar and K. Lovell, Stochastic Frontier Analysis, Cambridge University, Cambridge, 2000. 10.1017/CBO9781139174411Suche in Google Scholar
[24] T. Kuosmanen and M. Kortelainen, Stochastic non-smooth envelopment of data: Semi-parametric frontier estimation subject to shape constraints, J. Productivity Anal. 38 (2010), 11–28. 10.1007/s11123-010-0201-3Suche in Google Scholar
[25] C. Liu, A. Laporte and S. Ferguson, The quantile regression approach to efficiency measurement: Insights from Monte Carlo simulations, Health Econ. 17 (2008), 1073–1087. 10.1002/hec.1398Suche in Google Scholar PubMed
[26] W. Meeusen and J. van den Broeck, Efficiency estimation from Cobb–Douglas production functions with composed error, Internat. Econom. Rev. 1 (1977), 435–444. 10.2307/2525757Suche in Google Scholar
[27] A. Olson, P. Schmidt and M. Waldman, A Monte Carlo study of estimators of stochastic frontier production functions, J. Econometrics 13 (1980), 67–82. 10.1016/0304-4076(80)90043-3Suche in Google Scholar
[28] J. Ondrich and J. Ruggiero, Efficiency measurement in the stochastic frontier model, European J. Oper. Res. 129 (2001), 434–442. 10.1016/S0377-2217(99)00429-4Suche in Google Scholar
[29] L. Orea and S. Kumbhakar, Efficiency measurement using a stochastic frontier latent class model, Empirical Econ. 29 (2004), 169–183. 10.1007/s00181-003-0184-2Suche in Google Scholar
[30] C. Parmeter and S. Kumbhakar, Efficiency analysis: A primer on recent advances, Found. Trends Econ. 7 (2014), no. 34, 191–385. 10.1561/0800000023Suche in Google Scholar
[31] M. Pitt and L. Lee, The measurement and sources of technical inefficiency in the Indonesian weaving industry, J. Dev. Econ. 9 (1981), 43–64. 10.1016/0304-3878(81)90004-3Suche in Google Scholar
[32] J. Ruggiero, Efficiency estimation and error decomposition in the stochastic frontier model: A Monte Carlo analysis, European J. Oper. Res. 115 (1999), no. 3, 555–563. 10.1016/S0377-2217(98)00245-8Suche in Google Scholar
[33] J. Ruggiero, Data envelopment analysis with stochastic data, J. Oper. Res. Soc. 55 (2004), 1008–1012. 10.1057/palgrave.jors.2601779Suche in Google Scholar
[34] P. Schmidt and R. Sickles, Production frontiers and panel data, J. Bus. Econom. Statist. 2 (1984), no. 4, 367–374. 10.1080/07350015.1984.10509410Suche in Google Scholar
[35] D. Settlage, B. Dixon and M. Thomsen, A comparison of various frontier estimation methods under differing data generation assumptions, Staff Papers, Department of Agricultural Economics and Agribusiness, University of Arkansas, 2000. Suche in Google Scholar
[36] S. Shaik, Impact of liquidity risk on variations in efficiency and productivity: A panel gamma simulated maximum likelihood estimation, European J. Oper. Res. 245 (2015), no. 2, 463–469. 10.1016/j.ejor.2015.03.018Suche in Google Scholar
[37] L. Simar and P. Wilson, Inferences from cross-sectional, stochastic frontier models, Econometric Rev. 29 (2009), 62–98. 10.1080/07474930903324523Suche in Google Scholar
[38] D. Smith, Stochastic frontier models with dependent error components, Econom. J. 11 (2008), 172–192. 10.1111/j.1368-423X.2007.00228.xSuche in Google Scholar
[39] R. Stevenson, Likelihood functions for generalized stochastic frontier estimation, J. Econometrics 13 (1980), 57–66. 10.1016/0304-4076(80)90042-1Suche in Google Scholar
[40] M. Stone, How not to measure the efficiency of public services (and how one might), J. R. Stat. Soc. Ser. A 165 (2002), 405–434. 10.1111/1467-985X.00246Suche in Google Scholar
[41] M. Tsionas, When, where, and how of efficiency estimation: Improved procedures for stochastic frontier modeling, J. Amer. Statist. Assoc. 112 (2017), no. 519, 948–965. 10.1080/01621459.2016.1246364Suche in Google Scholar
[42] A. Zellner and N. Revankar, Generalized production functions, Rev. Econ. Stud. 36 (1969), no. 2, 241–250. 10.2307/2296840Suche in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- On the dependence structure and quality of scrambled (t, m, s)-nets
- Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process
- Body tail adaptive kernel density estimation for nonnegative heavy-tailed data
- Sensitivity analysis of stochastic frontier analysis models
Artikel in diesem Heft
- Frontmatter
- On the dependence structure and quality of scrambled (t, m, s)-nets
- Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process
- Body tail adaptive kernel density estimation for nonnegative heavy-tailed data
- Sensitivity analysis of stochastic frontier analysis models
