Abstract
Here we consider various cases where researchers are interested in measuring aggregate efficiency or productivity levels or their changes for a group of decision-making units. These could be an entire industry composed of individual firms, banks, and hospitals or a region composed of sub-regions or countries, or particular sub-groups of these units within a group, e.g., sub-groups of public vs. private or regulated vs. non-regulated firms, banks, or hospitals within the same industry, etc. Such analysis requires solutions to the aggregation problem – some theoretically justified approaches that can connect individual measures to aggregate measures. Various solutions are offered in the literature, and our goal is to try to coherently summarize at least some of them in this chapter. This material should be interesting not only for theorists but also (and perhaps more so) for applied researchers, as it provides exact formulas and intuitive explanations for various measures of group efficiency, group scale elasticity, and group productivity indexes and refers to original papers for more details.
The author acknowledges support of the University of Queensland and from the ARC grants (ARC FT170100401).
Notes
- 1.
A different area of the aggregation questions that focuses on the aggregation of inputs or aggregation of outputs for a firm (e.g., to reduce the dimension of the model) is not considered here and can be found in [51, 11, 6, 53] and the references therein. We also do not consider the question of aggregation of indexes with respect to different references (e.g., time periods) for the same firm, which can be found in [16] and the references therein.
- 2.
This chapter is a substantially revised, extended, and elaborated material that I presented earlier, in Chapter 5 of [47].
- 3.
While this is a generic example, a reader might have realized that many industries in the real world have a similar composition, often resembling the so-called Pareto principle, more casually known as “the 80/20 rule” postulating that about 80% share (e.g., of wealth, sales, etc.) is taken up by about 20% of members of a group.
- 4.
Lower efficiency of large firms is not unusual and often was reported in the literature. It can arise, for example, due to the greater complexity of being a larger organization involving greater levels of hierarchy and thus implying potentially greater principal-agent problems or requiring more inputs or higher costs than needed for producing the same level and the same quality of output.
- 5.
Indeed, later in this chapter, we will see that output shares are more coherent with output orientation, while for the input orientation it would be more natural to use the cost shares.
- 6.
This is not entirely surprising, e.g., recall that very strong assumptions are needed to establish positive aggregation results in consumer theory.
- 7.
- 8.
For theoretical results we do not require convexity of Ψk, although when implementing in practice one may impose it when choosing a particular estimator or particular functional form for technology.
- 9.
Note that for the aggregation results, a necessary assumption is the so-called Law of One Price, i.e., here it implies that all firms face the same output prices.
- 10.
We use ⊕ to distinguish the summation of sets (also called “Minkowski summation”) from the standard summation; e.g., see [37].
- 11.
- 12.
In the input-oriented context, such a benchmark will be the cost function, while in the framework where both input and output vectors can be changed when measuring efficiency (e.g., for efficiency based on the directional distance function or hyperbolic measures), the natural benchmark will be the profit function. We will briefly discuss these cases later in the chapter.
- 13.
- 14.
- 15.
- 16.
From theory, it is known that under the same weighting scheme, the geometric mean is larger than the harmonic mean but smaller than the arithmetic mean. Note however that the aggregate MPI in (65) involves products of ratios of the harmonic means and so it can be smaller or greater than the aggregate MPI obtained via a geometric mean as in (66), depending on the relative magnitudes that appear in the numerators and denominators of (65). Both means are approximately equal (to the arithmetic mean) in the sense of first order approximation around unity.
- 17.
One should however be careful aggregating when there are scores equal or very close to zero: both geometric and harmonic averages completely fail if at least one element is zero and may yield an unreasonably low aggregate score if at least one element is very close to zero (even if many others have large efficiency or productivity scores), unless they are “neutralized” by a very low weight in the aggregation, as can be done with weighted aggregates. In such cases, using arithmetic aggregation, which is less sensitive to the outliers, could also be a better solution.
- 18.
For example, see [39].
- 19.
- 20.
- 21.
- 22.
More recently, another definition of aggregate technology, which involved the union of technology sets, was considered by [40, 41], which later was shown to be equivalent to the Koopmans-type aggregate technology \(\Psi _{\tau }^{*}\), under standard regularity conditions of production theory (see [47]).
- 23.
Here, note that we allow for different time subscripts for inputs and outputs for the framework to be compatible with the HMPI context.
- 24.
Example, see [47], and the relevant chapters “Data Envelopment Analysis: A Nonparametric Method of Production Analysis,” “Stochastic Frontier Analysis: Foundations and Advances I,” and “Stochastic Frontier Analysis: Foundations and Advances II” in this Handbook.
- 25.
Also see [55] for this and other related results.
References
Blackorby C, Russell RR (1999) Aggregation of efficiency indices. J Prod Anal 12(1):5–20
Cooper W, Huang Z, Li S, Parker B, Pastor J (2007) Efficiency aggregation with enhanced Russell measures in data envelopment analysis. Socio Econ Plan Sci 41(1):1–21
Domar ED (1961) On the measurement of technological change. Econ J 71(284):709–729
Färe R, Grosskopf S, Lindgren B, Roos P (1994) Productivity developments in Swedish hospitals: a Malmquist output index approach. In: Charnes A, Cooper W, Lewin AY, Seiford LM (eds) Data envelopment analysis: theory, methodology and applications. Kluwer Academic Publishers, Boston, pp 253–272
Färe R, Grosskopf S, Lovell CAK (1986) Scale economies and duality. Zeitschrift für Nationalökonomie/J Econ 46(2):175–182
Färe R, Grosskopf S, Zelenyuk V (2004) Aggregation bias and its bounds in measuring technical efficiency. Appl Econ Lett 11(10):657–660. https://doi.org/10.1080/1350485042000207243
Färe R, Grosskopf S, Zelenyuk V (2004) Aggregation of cost efficiency: indicators and indexes across firms. Acad Econ Pap 32(3):395–411
Fare R, Grosskopf S, Zelenyuk V (2008) Aggregation of nerlovian profit indicator. Appl Econ Lett 15(11):845–847
Färe R, Karagiannis G (2014) A postscript on aggregate Farrell efficiencies. Eur J Oper Res 233(3):784–786
Färe R, Primont D (1995) Multi-output production and duality: theory and applications. Kluwer Academic Publishers, New York
Färe R, Zelenyuk V (2002) Input aggregation and technical efficiency. Appl Econ Lett 9(10):635–636
Färe R, Zelenyuk V (2003) On aggregate Farrell efficiencies. Eur J Oper Res 146(3):615–620
Färe R, Zelenyuk V (2005) On Farrell’s decomposition and aggregation. Int J Bus Econ 4(2):167–171
Färe R, Zelenyuk V (2007) Extending Färe and Zelenyuk 2003. Eur J Oper Res 179(2):594–595
Färe R, Zelenyuk V (2012) Aggregation of scale elasticities across firms. Appl Econ Lett 19(16):1593–1597
Färe R, Zelenyuk V (2019) On luenberger input, output and productivity indicators. Econ Lett 179:72–74
Farrell MJ (1957) The measurement of productive efficiency. J R Stat Soc Ser A (General) 120(3):253–290
Ferrier G, Leleu H, Valdmanis V (2009) Hospital capacity in large urban areas: is there enough in times of need? J Prod Anal 32(2):103–117
Førsund FR, Hjalmarsson L (1979) Generalised Farrell measures of efficiency: an application to milk processing in Swedish dairy plants. Econ J 89(354):294–315. http://ww.jstor.org/stable/2231603
Färe R, Karagiannis G (2017) The denominator rule for share-weighting aggregation. Eur J Oper Res 260(3):1175–1180. https://ideas.repec.org/a/eee/ejores/v260y2017i3p1175-1180.html
Hall MJ, Kenjegalievaa KA, Simper R (2012) Environmental factors affecting Hong Kong banking: a post-Asian financial crisis efficiency analysis. Glob Financ J 23(3):184–201
Henderson DJ, Zelenyuk V (2007) Testing for (efficiency) catching-up. South Econ J 73(4):1003–1019. http://www.jstor.org/stable/20111939
Karagiannis G (2015) On structural and average technical efficiency. J Prod Anal 43(3):259–267
Karagiannis G, Lovell CAK (2015) Productivity measurement in radial DEA models with a single constant input. Eur J Oper Res 251(1):323–328
Koopmans T (1957) Three essays on the state of economic science. McGraw-Hill, New York
Krein M, Smulian V (1940) On regulary convex sets in the space conjugate to a Banach space. Ann Math 41(2):556–583
Kuosmanen T, Cherchye L, Sipiläinen T (2006) The law of one price in data envelopment analysis: Restricting weight flexibility across firms. Eur J Oper Res 170(3):735–757
Kuosmanen T, Kortelainen M, Sipiläinen T, Cherchye L (2010) Firm and industry level profit efficiency analysis using absolute and uniform shadow prices. Eur J Oper Res 202(2): 584–594
Li SK, Cheng YS (2007) Solving the puzzles of structural efficiency. Eur J Oper Res 180(2):713–722
Li S-K, Ng YC (1995) Measuring the productive efficiency of a group of firms. Int Adv Econ Res 1(4):377–390
Mayer A, Zelenyuk V (2014) Aggregation of Malmquist productivity indexes allowing for reallocation of resources. Eur J Oper Res 238(3):774–785
Mayer A, Zelenyuk V (2014) An aggregation paradigm for Hicks-Moorsteen productivity indexes, cEPA Working Paper No. WP01/2014
Mayer A, Zelenyuk V (2019) Aggregation of individual efficiency measures and productivity indices. In: ten Raa T, Greene W (eds) The Palgrave Handbook of Economic Performance Analysis. Palgrave Macmillan, Cham. https://link.springer.com/chapter/10.1007/978-3-030-23727-1_14#citeas
Mugera A, Ojede A (2014) Technical efficiency in African agriculture: is it catching up or lagging behind? J Int Dev 26(6):779–795
Mussard S, Peypoch N (2006) On multi-decomposition of the aggregate Malmquist productivity index. Econ Lett 91(3):436–443
Nesterenko V, Zelenyuk V (2007) Measuring potential gains from reallocation of resources. J Prod Anal 28(1–2):107–116
Oks E, Sharir M (2006) Minkowski sums of monotone and general simple polygons. Discret Comput Geom 35(2):223–240
Pachkova EV (2009) Restricted reallocation of resources. Eur J Oper Res 196(3):1049–1057
Panzar JC, Willig RD (1977) Free entry and the sustainability of natural monopoly. Bell J Econ 8(1):1–22
Peyrache A (2013) Industry structural inefficiency and potential gains from mergers and break-ups: a comprehensive approach. Eur J Oper Res 230(2):422–430
Peyrache A (2015) Cost constrained industry inefficiency. Eur J Oper Res 247(3):996–1002
Pilyavsky A, Staat M (2008) Efficiency and productivity change in Ukrainian health care. J Prod Anal 29(2):143–154
Raa TT (2011) Benchmarking and industry performance. J Prod Anal 36(3):285–292
Schneider R (1993) Convex bodies: the Brunn-Minkowski Theory. Cambridge University Press, New York
Shephard RW (1953) Cost and production functions. Princeton University Press, Princeton
Shephard RW (1970) Theory of cost and production functions. Princeton studies in mathematical economics. Princeton University Press, Princeton
Sickles R, Zelenyuk V (2019) Measurement of productivity and efficiency: theory and practice. Cambridge University Press, Cambridge. https://doi.org/10.1017/9781139565981
Simar L, Zelenyuk V (2007) Statistical inference for aggregates of Farrell-type efficiencies. J Appl Econ 22(7):1367–1394. http://ideas.repec.org/a/jae/japmet/v22y2007i7p1367-1394.html
Simar L, Zelenyuk V (2018) Central limit theorems for aggregate efficiency. Oper Res 166(1):139–149
Starr RM (2008) Shapley-Folkman theorem. In: Durlauf SN, Blume LE (eds) The new palgrave dictionary of economics. Palgrave Macmillan, Basingstoke, pp 317–318
Tauer LW (2001) Input aggregation and computed technical efficiency. Appl Econ Lett 8:295–297
Weill L (2008) On the inefficiency of European socialist economies. J Prod Anal 29(2):79–89
Wilson PW (2018) Dimension reduction in nonparametric models of production. Eur J Oper Res 267(1):349–367. http://www.sciencedirect.com/science/article/pii/S0377221717310317
Ylvinger S (2000) Industry performance and structural efficiency measures: solutions to problems in firm models. Eur J Oper Res 121(1):164–174
Zelenyuk V (2002) Essays in efficiency and productivity analysis of economic systems. Ph.D. thesis, Oregon State University, Corvallis
Zelenyuk V (2006) Aggregation of Malmquist productivity indexes. Eur J Oper Res 174(2):1076–1086
Zelenyuk V (2013) A scale elasticity measure for directional distance function and its dual: theory and DEA estimation. Eur J Oper Res 228(3):592–600. http://ideas.repec.org/a/eee/ejores/v228y2013i3p592-600.html
Zelenyuk V (2013) A note on equivalences in measuring returns to scale. Int J Bus Econ 12(1):85–89. http://ideas.repec.org/a/ijb/journl/v12y2013i1p85-89.html
Zelenyuk V (2015) Aggregation of scale efficiency. Eur J Oper Res 240(1):269–277
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this entry
Cite this entry
Zelenyuk, V. (2020). Aggregation of Efficiency and Productivity: From Firm to Sector and Higher Levels. In: Ray, S., Chambers, R., Kumbhakar, S. (eds) Handbook of Production Economics. Springer, Singapore. https://doi.org/10.1007/978-981-10-3450-3_19-1
Download citation
DOI: https://doi.org/10.1007/978-981-10-3450-3_19-1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3450-3
Online ISBN: 978-981-10-3450-3
eBook Packages: Springer Reference Economics and FinanceReference Module Humanities and Social SciencesReference Module Business, Economics and Social Sciences