Abstract
The free disposal hull (FDH) model of production technology assumes free disposability of all inputs and outputs, but does not make any convexity assumptions. In this paper, we develop an algorithm for the reconstruction of the frontier of the FDH technology that corresponds to its sections by different two-dimensional planes. From a practical perspective, the suggested algorithm is useful for the visualization and exploration of the efficient frontier of the FDH technology. Furthermore, based on the suggested algorithm, we develop a new procedure for the evaluation of returns to scale in the FDH technology. Compared to the existing methods, our approach does not require assessing the efficiency of productive units in the reference technologies, which is known to be a computationally intensive task. Our theoretical results are confirmed by computational experiments in applications with real-life data sets from different industries.
Similar content being viewed by others
Notes
Banker, Cooper, Seiford and Zhu [27], Zelenyuk [28], Sahoo and Tone [29] and Krivonozhko, Førsund and Lychev [30] provide reviews of recent developments of the literature on RTS. Podinovski, Chambers, Atici and Deineko [31] extend the notion of RTS based on the one-sided scale elasticity to any technology which is a polyhedral set. Podinovski [23] develops a further extension of RTS to any convex technology.
It is worth noting that, without any additional assumptions or heuristic rules, the standard notion of local RTS in the FDH technology is trivial and uninteresting. Indeed, at any efficient observed DMU in the FDH technology, the right-hand scale elasticity is equal to zero and the left-hand scale elasticity is undefined (or can be formally taken equal to \( + \infty \)). Therefore, every efficient DMU in the FDH technology exhibits decreasing RTS on the right and increasing RTS on the left. Cesaroni et al. [19] suggest an alternative definition of local RTS in the FDH technology which takes into account the ray average productivity of DMUs in some small but finite (not marginal) ε-neighbourhood of the DMU under the assessment. The resulting RTS characterization depends on the value of ε chosen by the analyst.
By definition, DMU \(({{X}_{o}},{{Y}_{o}})\) is (strongly) efficient if there exists no DMU \((X',Y') \in {{T}_{{{\text{FDH}}}}}\) such that \(X' \leqslant {{X}_{o}}\), \(Y' \geqslant {{Y}_{o}}\), and \(({{X}_{o}},{{Y}_{o}}) \ne (X',Y')\). The assumption that DMU \(({{X}_{o}},{{Y}_{o}})\) is strongly efficient is not necessary and made only in order to simplify the exposition. For example, for the notion of (global) RTS to be correctly defined, it suffices to assume that DMU \(({{X}_{o}},{{Y}_{o}})\) is only output radial efficient in technology \({{T}_{{{\text{FDH}}}}}\). In order to evaluate RTS using the input-oriented programs (2) and (3), we need to assume that DMU \(({{X}_{o}},{{Y}_{o}})\) is both input and output radial efficient [16, pp. 243–244]. This is clearly a weaker assumption than the assumption of strong efficiency.
REFERENCES
F. R. Førsund and L. Hjalmarsson, “Calculating scale elasticity in DEA models,” J. Operat. Res. Soc. 55 (10), 1023–1038 (2004).
R. D. Banker, A. Charnes, and W. W. Cooper, “Some models for estimating technical and scale inefficiencies in data envelopment analysis,” Management Sci. 30 (9), 1078–1092 (1984).
R. D. Banker and R. M. Thrall, “Estimation of returns to scale using data envelopment analysis,” Eur. J. Operat. Res. 62 (1), 74–84 (1992).
P. Hadjicostas and A. C. Soteriou, “One-sided elasticities and technical efficiency in multi-output production: A theoretical framework,” Eur. J. Operat. Res. 168 (2), 425–449 (2006).
R. G. Chambers and R. Färe, “A 'calculus' for data envelopment analysis,” J. Productivity Anal. 30 (3), 169–175 (2008).
V. V. Podinovski, F. R. Førsund, and V. E. Krivonozhko, “A simple derivation of scale elasticity in data envelopment analysis,” Eur. J. Operat. Res. 197 (1), 149–153 (2009).
V. V. Podinovski and F. R. Førsund, “Differential characteristics of efficient frontiers in data envelopment analysis,” Operat. Res. 58 (6), 1743–1754 (2010).
D. Deprins, L. Simar, and H. Tulkens, “Measuring labor-efficiency in post offices,” in The Performance of Public Enterprises: Concepts and Measurements, Ed. by M. Marchand, P. Pestieau, and H. Tulkens (North-Holland, Amsterdam, 1984), pp. 243–267.
K. Kerstens and P. Vanden Eeckaut, “Estimating returns to scale using non-parametric deterministic technologies: A new method based on goodness-of-fit,” Eur. J. Operat. Res. 113 (1), 206–214 (1999).
W. Briec, K. Kerstens, H. Leleu, and P. Vanden Eeckaut, “Returns to scale on nonparametric deterministic technologies: Simplifying goodness-of-fit methods using operations on technologies,” J. Productivity Anal. 14 (3), 267–274 (2000).
R. Färe, S. Grosskopf, and C. A. K. Lovell, “The structure of technical efficiency,” Scand. J. Econ. 85 (2), 181–190 (1983).
R. Färe, S. Grosskopf, and C. A. K. Lovell, The Measurement of Efficiency of Production (Kluwer, Boston, 1985).
V. V. Podinovski, “On the linearization of reference technologies for testing returns to scale in FDH models,” Eur. J. Operat. Res. 152 (3), 800–802 (2004).
M. Soleimani-damaneh, G. R. Jahanshahloo, and M. Reshadi, “On the estimation of returns-to-scale in FDH models,” Eur. J. Operat. Res. 174 (2), 1055–1059 (2006).
H. Leleu, “A linear programming framework for free disposal hull technologies and cost functions: Primal and dual models,” Eur. J. Operat. Res. 168 (2), 340–344 (2006).
V. V. Podinovski, “Efficiency and returns to scale on the 'no free lunch' assumption only,” J. Productivity Anal. 22 (3), 227–257 (2004).
V. V. Podinovski, “Local and global returns to scale in performance measurement,” J. Operat. Res. Soc. 55 (2), 170–178 (2004).
R. D. Banker, “Estimating most productive scale size using data envelopment analysis,” Eur. J. Operat. Res. 17 (1), 35–44 (1984).
G. Cesaroni, K. Kerstens, and I. Van de Woestyne, “Global and local scale characteristics in convex and nonconvex nonparametric technologies: A first empirical exploration,” Eur. J. Operat. Res. 259 (2), 576–586 (2017).
V. E. Krivonozhko, O. B. Utkin, A. V. Volodin, I. A. Sablin, and M. Patrin, “Constructions of economic functions and calculations of marginal rates in DEA using parametric optimization methods,” J. Operat. Res. Soc. 55 (10), 1049–1058 (2004).
V. E. Krivonozhko and A. V. Lychev, “Algorithms for construction of efficient frontier for nonconvex models on the basis of optimization methods,” Dokl. Math. 96 (2), 541–544 (2017).
V. E. Krivonozhko, A. V. Lychev, and E. A. Kalashnikov, “Constructions of input and output isoquants for nonconvex multidimensional models,” Proceedings of the OPTIMA-2017 Conference, Petrovac, Montenegro, October 2–7, 2017, Ed. by Yu. G. Evtushenko, M. Yu. Khachay, O. V. Khamisov, Yu. A. Kochetov, V. U. Malkova, and M. A. Posypkin, pp. 336–342.
V. V. Podinovski, “Returns to scale in convex production technologies,” Eur. J. Operat. Res. 258 (3), 970–982 (2017).
F. R. Førsund, L. Hjalmarsson, V. E. Krivonozhko, and O. B. Utkin, “Calculation of scale elasticities in DEA models: Direct and indirect approaches,” J. Productivity Anal. 28 (1–2), 45–56 (2007).
V. E. Krivonozhko, F. R. Førsund, and A. V. Lychev, “A note on imposing strong complementary slackness conditions in DEA,” Eur. J. Operat. Res. 220 (3), 716–721 (2012).
Lp_Solve Reference Guide, http://lpsolve.sourceforge.net/5.5/. Accessed April 24, 2018.
R. D. Banker, W. W. Cooper, L. M. Seiford, and J. Zhu, “Returns to scale in DEA,” Handbook on Data Envelopment Analysis, Ed. by W. W. Cooper, L. Seiford, and J. Zhu, 2nd ed. (Springer Science + Business Media, New York, 2011), pp. 41–70.
V. Zelenyuk, “A scale elasticity measure for directional distance function and its dual: Theory and DEA estimation,” Eur. J. Operat. Res. 228 (3), 592–600 (2013).
B. K. Sahoo and K. Tone, “Scale elasticity in non-parametric DEA approach,” in Data Envelopment Analysis: A Handbook of Models and Methods, Ed. by J. Zhu (Springer Science + Business Media, New York, 2015), pp. 269–290.
V. E. Krivonozhko, A. V. Lychev, and F. R. Førsund, “Measurement of returns to scale in radial DEA models,” Comput. Math. Math. Phys. 57 (1), 83–93 (2017).
V. V. Podinovski, R. G. Chambers, K. B. Atici, and I. D. Deineko, “Marginal values and returns to scale for nonparametric production frontiers,” Operat. Res. 64 (1), 236–250 (2016).
V. E. Krivonozhko and A. V. Lychev, “Frontier visualization for nonconvex models with the use of purposeful enumeration methods,” Dokl. Akad. Nauk 96 (3), 650–653 (2017).
ACKNOWLEDGMENTS
This study is supported by the Russian Science Foundation (project no. 17-11-01353). The authors are grateful to V.V. Podinovski whose suggestions have led to improvements of this paper.
Author information
Authors and Affiliations
Corresponding authors
Additional information
The article was translated by the authors.
Rights and permissions
About this article
Cite this article
Krivonozhko, V.E., Lychev, A.V. Frontier Visualization and Estimation of Returns to Scale in Free Disposal Hull Models. Comput. Math. and Math. Phys. 59, 501–511 (2019). https://doi.org/10.1134/S0965542519030114
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0965542519030114