Abstract
In the stochastic frontier model, we extend the multivariate probability statements of Horrace (J Econom, 126:335–354, 2005) to calculate the conditional probability that a firm is any particular efficiency rank in the sample. From this, we construct the conditional expected efficiency rank for each firm. Compared to the traditional ranked efficiency point estimates, firm-level conditional expected ranks are more informative about the degree of uncertainty of the ranking. The conditional expected ranks may be useful for empiricists. A Monte Carlo study and an empirical example are provided.
Similar content being viewed by others
Notes
A fixed effect model is also considered in Schmidt and Sickles (1984).
See, for example, Sect. 5.2.2 of Reingold et al. (1977) for an efficient algorithm that serves to find \(N_i^{l-}(r)\) and \(N_i^{l+}(r)\) for \(l=1,\ldots ,{}_{n-1}C_{r-1}\).
One could supplement the conditional means with the conditional prediction intervals of Horrace and Schmidt (1996), to judge how much the marginal distributions overlap. The degree of overlap may correspond to the extent to which the conditional probabilities and expected ranks are close to their unconditional counterparts, but this might be highly subjective and (perhaps) lead to an inaccurate assessment of the nature of efficiency in the population.
Feng and Horrace are only concerned with detecting the best firm. We want to detect the rank of all firms.
The nomenclature “mostly stars and dogs” is due to Almanidis et al. (2014).
The skew of a truncated normal is necessarily positive. We use the “standardized” definition of skew where the 3rd central moment is divided by the third power of the standard deviation.
Again, the probabilities in (2) could be easily simulated for large \(n\), but for the purposes of illustration, small \(n\) is sufficient.
These results are consistent with the Feng and Horrace (2012).
We thank an anonymous referee for these insights into the information contained in the quantiles, which may imply that a resampling method, such as bootstrap, may provide better estimates of expected rank.
The results of the estimation are not reproduced here to focus attention on the different characterization of efficiency ranks and the importance of the proposed conditional expected rank statistic.
The expected ranks are calculated using the conditional efficiency rank probabilities for only these five vessels in each tier. In particular we did not calculate the efficiency rank probabilities for all vessels, and calculate expected rank only for these five, based on the probabilities from all vessels.
When conditional expected ranks are based on simulated probabilities, the simulation sample size is always 5,000.
References
Ahn SC, Lee YH (2007) Panel data models with multiple time-varying individual effects. J Prod Anal 27:1–12
Aigner DJ, Lovell CAK, Schmidt P (1977) Formulation and estimation of stochastic frontier production functions. J Econom 6:21–37
Almanidis P, Qian J, Sickles RC (2014) Stochastic frontiers with bounded inefficiency. In: Sickles RC, Horrace WC (eds) Festschrift in honor of Peter Schmidt: Econometric methods and applications. Springer Science & Business Media, New York, pp 47–81
Battese GE, Coelli TJ (1988) Prediction of firm-level technical efficiencies with a generalized frontier production function and panel data. J Econom 38:387–399
Battese GE, Coelli TJ (1992) Frontier production functions, technical efficiency and panel data: with application to paddy farmers in India. J Prod Anal 3:153–170
Battese GE, Coelli TJ (1995) A model for technical inefficiency effects in a stochastic frontier production function for panel data. Empir Econ 20:325–332
Bechhofer RE (1954) A single-sample multiple decision procedure for ranking means of normal populations with known variances. Ann Math Stat 25:16–39
Chen YY, Schmidt P, Wang HJ, (2011) Consistent estimation of the fixed effects stochastic frontier model. Unpublished manuscript
Colombi R, Kumbhakar SC, Martinix G, Vittadini G (forthcoming) Closed-skew normality in stochastic frontiers with individual effects and long/short-run efficiency. J Prod Anal
Cornwell C, Schmidt P, Sickles R (1990) Production frontiers with cross-sectional and time-series variation in efficiency levels. J Econom 46:185–200
Cuesta RA (2000) A production model with firm-specific temporal variation in technical efficiency: with application to Spanish dairy farms. J Prod Anal 13:139–158
Dunnett CW (1955) A multiple comparison procedure for comparing several treatments with a control. J Am Stat Assoc 50:1096–1121
El-Gamal M, Grether D (1995) Are people Bayesian? Uncovering behavior strategies. J Am Stat Assoc 90:1137–1145
El-Gamal M, Grether D (2000) Changing decision rules: Uncovering behavioral strategies using estimation classification (EC). In: Machina M et al. (eds) Preferences, beliefs, and attributes in decision making. Kluwer, New York
Feng Q, Horrace WC (2012) Alternative technical efficiency measures: skew, bias and scale. J Appl Econom 27:253–268
Flores-Lagunes A, Horrace WC, Schnier KE (2007) Identifying technically efficient fishing vessels: a non-empty, minimal subset approach. J Appl Econom 22:729–745
Greene WH (1990) A gamma distributed stochastic frontier model. J Econom 46:141–163
Greene WH (2005) Reconsidering heterogeneity in panel data estimators of the stochastic frontier model. J Econom 126:269–303
Gupta SS (1956) On a decision rule for a problem of ranking means. Institute of Statistics Mimeo Series No. 150, University of North Carolina
Gupta SS (1965) On some multiple decision (selection and ranking) rules. Technometrics 7:225–245
Han C, Orea L (2005) Estimation of panel data model with parametric temporal variation in individual effects. J Econom 126:241–267
Horrace WC (2005) On ranking and selection from independent truncated normal distributions. J Econom 126:335–354
Horrace WC, Schmidt P (1996) Confidence statements for efficiency estimates from stochastic frontier models. J Prod Anal 7:257–282
Jondrow J, Lovell CAK, Materov IS, Schmidt P (1982) On the estimation of technical efficiency in the stochastic production function model. J Econom 19:233–238
Kumbhakar SC (1990) Production frontiers, panel data, and time-varying technical inefficiency. J Econom 46:201–211
Kumbhakar SC, Lien G, Hardaker JB (2012) Technical efficiency in competing panel data models: a study of Norwegian grain farming. J Prod Anal. doi:10.1007/s11123-012-0303-1
Lee YH (2006) A stochastic production frontier model with group-specific temporal variation in technical efficiency. Eur J Oper Res 174(3):1616–1630
Lee YH, Schmidt P (1993) A production frontier model with flexible temporal variation in technical inefficiency. In: Fried H, Lovell CAK, Schmidt P (eds) The measurement of productivity efficiency: techniques and applications. Oxford University Press, Oxford
Olson JA, Schmidt P, Waldman DM (1980) A Monte Carlo study of estimators of stochastic frontier production functions. J Econom 13:67–82
Reingold EM, Nievergelt J, Deo N (1977) Combinatorial algorithms: theory and practice. Prentice Hall, New York
Schmidt P, Sickles RC (1984) Production frontiers and panel data. J Bus Econ Stat 2:367–374
Silverman BW (1986) Density estimation for statistics and data analysis. Chapman and Hall, London
Simar L, Wilson PW (2009) Inferences from cross-sectional, stochastic frontier models. Econom Rev 29:62–98
Wheat P, Greene WH, Smith A (forthcoming) Understanding prediction intervals for firm specific inefficiency scores from parametric stochastic frontier models. J Prod Anal
Acknowledgments
The authors are grateful to Peng Liu for excellent research assistance and to several anonymous referees for their suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Horrace, W.C., Richards-Shubik, S. & Wright, I.A. Expected efficiency ranks from parametric stochastic frontier models. Empir Econ 48, 829–848 (2015). https://doi.org/10.1007/s00181-014-0808-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00181-014-0808-8