Calculating scale elasticity in DEA models

In the data envelopment analysis (DEA) efficiency literature, qualitative characterizations of returns to scale (increasing, constant, or decreasing) are most common. In economics it is standard to use the scale elasticity as a quantification of scale properties for a production function representing efficient operations. Our contributions are to review DEA practices, apply the concept of scale elasticity from economic multi-output production theory to DEA piecewise linear frontier production functions, and develop formulas for scale elasticity for radial projections of inefficient observations in the relative interior of fully dimensional facets. The formulas are applied to both constructed and real data and show the differences between scale elasticities for the two valid projections (input and output orientations). Instead of getting qualitative measures of returns to scale only as was done earlier in the DEA literature, we now get a quantitative range of scale elasticity values providing more information to policy-makers.     

A new non-oriented model for classifying flexible measures in DEA

In conventional data envelopment analysis (DEA), measures are classified as either input or output. However, in some real cases there are variables which act as both input and output and are known as flexible measures. Most of the previous suggested models for determining the status of flexible measures are oriented. One important issue of these models is that unlike standard DEA, even under constant returns to scale the input- and output-oriented model may produce different efficiency scores. Also, can be expected a flexible measure is selected as an input variable in one model but an output variable in the other model. In addition, in all of the previous studies did not point to variable returns to scale (VRS), but the VRS assumption is prevailed on many real applications. To deal with these issues, this study proposes a new non-oriented model that not only selects the status of each flexible measure as an input or output but also determines returns to scale status. Then, the aggregate model and an extension with the negative data related to the proposed approach are presented.     

Measuring inefficiency for specific inputs using data envelopment analysis: evidence from construction industry in Spain and Portugal

This article contributes to the efficiency literature by defining, in the context of the data envelopment analysis framework, the directional distance function approach for measuring both technical and scale inefficiencies with regard to the use of individual inputs. The input-specific technical and scale inefficiencies are then aggregated in order to calculate the overall inefficiency measures. Empirical application focuses on a large dataset of Spanish and Portuguese construction companies between 2002 and 2010 and accounts for three inputs: materials, labor and fixed assets. The results show, first, that for both Spanish and Portuguese construction companies, fixed assets are the most technically inefficient input. Second, the most inefficient scale concerns the utilization of material input in both samples; the reason for this inefficiency is that firms tend to operate in the increasing returns to scale portion of technology set. Third, in both samples, large firms have the lowest input-specific technical inefficiencies, but the highest input-specific scale inefficiencies, compared to their small and medium-sized counterparts, and tend to suffer from decreasing returns to scale. Finally, in both samples, input-specific technical inefficiency under constant returns to scale increased during the period of the recent financial crisis, mainly due to the augmentation in scale inefficiency.

     

Additive efficiency decomposition in two-stage DEA

Kao and Hwang (2008) [Kao, C., Hwang, S.-N., 2008. Efficiency decomposition in two-stage data envelopment analysis: An application to non-life insurance companies in Taiwan. European Journal of Operational Research 185 (1), 418–429] develop a data envelopment analysis (DEA) approach for measuring efficiency of decision processes which can be divided into two stages. The first stage uses inputs to generate outputs which become the inputs to the second stage. The first stage outputs are referred to as intermediate measures. The second stage then uses these intermediate measures to produce outputs. Kao and Huang represent the efficiency of the overall process as the product of the efficiencies of the two stages. A major limitation of this model is its applicability to only constant returns to scale (CRS) situations. The current paper develops an additive efficiency decomposition approach wherein the overall efficiency is expressed as a (weighted) sum of the efficiencies of the individual stages. This approach can be applied under both CRS and variable returns to scale (VRS) assumptions. The case of Taiwanese non-life insurance companies is revisited using this newly developed approach.     

Aggregation of scale efficiency

In this article we generalize the aggregation theory in efficiency and productivity analysis by deriving solutions to the problem of aggregation of individual scale efficiency measures, primal and dual, into aggregate primal and dual scale efficiency measures of a group (e.g., industry). The new aggregation result is coherent with aggregation framework and solutions that were earlier derived for other related efficiency measures and can be used in practice for estimation of scale efficiency of an industry or other groups of firms within it.     

The Indian auto component industry – Estimation of operational efficiency and its determinants using DEA

In this paper, the performance analysis of the Indian auto component industry is carried out from the perspectives of an original equipment manufacturer and a component supplier. Various efficiency measures are estimated using Data Envelopment Analysis with publicly available financial data on a representative sample of 50 firms. The first stage analysis reveals various operational inefficiencies in the auto component industry which are subsequently decomposed into technical, input mix and scale efficiencies. The study finds evidence that a majority of the inefficient firms are operating in the diminishing returns to scale region and demonstrates potential savings through benchmark input targets. A second stage analysis aimed at exploring root causes of inefficiencies finds that substitution of labour for capital could be causing a variety of inefficiencies including the input mix inefficiency in the Indian component industry. The empirical results also suggest that, unlike the global auto supply chain, higher average inventories are required for higher operational efficiencies in the Indian context. Contrary to the popular expectations, the technology licensing does not show significant influence on efficiency, at least in the short term, whereas efficient working capital management does result in higher operational efficiencies. The study also unearths the need to reform labour laws which are significantly contributing to various inefficiencies in the Indian component industry.     

DEA model with shared resources and efficiency decomposition

Data envelopment analysis (DEA) has proved to be an excellent approach for measuring performance of decision making units (DMUs) that use multiple inputs to generate multiple outputs. In many real world scenarios, DMUs have a two-stage network process with shared input resources used in both stages of operations. For example, in hospital operations, some of the input resources such as equipment, personnel, and information technology are used in the first stage to generate medical record to track treatments, tests, drug dosages, and costs. The same set of resources used by first stage activities are used to generate the second-stage patient services. Patient services also use the services generated by the first stage operations of housekeeping, medical records, and laundry. These DMUs have not only inputs and outputs, but also intermediate measures that exist in-between the two-stage operations. The distinguishing characteristic is that some of the inputs to the first stage are shared by both the first and second stage, but some of the shared inputs cannot be conveniently split up and allocated to the operations of the two stages. Recognizing this distinction is critical for these types of DEA applications because measuring the efficiency of the production for first-stage outputs can be misleading and can understate the efficiency if DEA fails to consider that some of the inputs generate other second-stage outputs. The current paper develops a set of DEA models for measuring the performance of two-stage network processes with non splittable shared inputs. An additive efficiency decomposition for the two-stage network process is presented. The models are developed under the assumption of variable returns to scale (VRS), but can be readily applied under the assumption of constant returns to scale (CRS). An application is provided.     

Measuring super-efficiency in DEA in the presence of infeasibility

Super-efficiency data envelopment analysis (DEA) model is obtained when a decision making unit (DMU) under evaluation is excluded from the reference set. Because of the possible infeasibility of super-efficiency DEA model, the use of super-efficiency DEA model has been restricted to the situations where constant returns to scale (CRS) are assumed. It is shown that one of the input-oriented and output-oriented super-efficiency DEA models must be feasible for a any efficient DMU under evaluation if the variable returns to scale (VRS) frontier consists of increasing, constant, and decreasing returns to scale DMUs. We use both input- and output-oriented super-efficiency models to fully characterize the super-efficiency. When super-efficiency is used as an efficiency stability measure, infeasibility means the highest super-efficiency (stability). If super-efficiency is interpreted as input saving or output surplus achieved by a specific efficient DMU, infeasibility does not necessary mean the highest super-efficiency.     

Input, output and graph technical efficiency measures on non-convex FDH models with various scaling laws: An integrated approach based upon implicit enumeration algorithms

In a recent article, Briec, Kerstens and Vanden Eeckaut (2004) develop a series of nonparametric, deterministic non-convex technologies integrating traditional returns to scale assumptions into the non-convex FDH model. They show, among other things, how the traditional technical input efficiency measure can be analytically derived for these technology specifications. In this paper, we develop a similar approach to calculate output and graph measures of technical efficiency and indicate the general advantage of such solution strategy via enumeration. Furthermore, several analytical formulas are established and some algorithms are proposed relating the three measurement orientations to one another.     

Scale characterizations in a DEA directional technology distance function framework

The present study extends prior research on data envelopment analysis (DEA)-based returns to scale in view of the fact that the standard methods are very restrictive. The extension is made in the context of the directional technology distance function that generalizes the Shephard input and output distance functions. The two main results in this extended setting are as follows. First, we show how Banker's most productive scale size (MPSS) concept is characterized. Second, we obtain scale elasticity measures and examine the properties and the relationships with standard scale elasticity measures.     

Regional concentration and efficiency in Mexican manufacturing

This paper explores the link between industrial location, concentration, and economic efficiency in Mexican manufacturing. Using a linear programming approach, the authors calculate indices of overall, technical, allocative, and scale efficiency for Mexican manufacturing industries by state to test whether, in 1985, those regions with high levels of industrial concentration were suffering from the costs of congestion. The evidence suggests that, at least at the aggregate level, there continued to be a positive relationship between industry concentration and efficiency in production. There is also evidence that overall efficiency was related to scale efficiency, although highly industrialized regions on the production frontier often operated at inefficient scales. In particular, the most concentrated regions (the Federal District, the state of Mexico, Jalisco, and Nuevo León) consistently display decreasing returns to scale, indicating that the process of industrial concentration may be leading to diseconomies of scale. Finally, an econometric analysis suggests that scale, urbanization, and agglomeration economies are positively related to overall and technical efficiency at the regional level, while foreign ownership is negatively related. Agglomeration economies at the industry level were not significant. The paper also makes a methodological contribution. It is the first application of a distance-function production methodology to measuring regional efficiency in a developing country. It demonstrates how to conduct distance-function efficiency analysis using the newly developed GAMS mathematical programming environment. These tools should be of considerable interest to applied microeconomists.     

DEA environmental assessment: Measurement of damages to scale with unified efficiency under managerial disposability or environmental efficiency

This study proposes a use of Data Envelopment Analysis (DEA) for environmental assessment. Firms usually produce not only desirable but also undesirable outputs as a result of their economic activities. The concept of disposability on undesirable outputs is separated into natural and managerial disposability. Natural disposability is an environmental strategy in which firms decrease their inputs to reduce a vector of undesirable outputs. Given the reduced input vector, they attempt to increase desirable outputs as much as possible. Managerial disposability involves the opposite strategy of increasing an input vector. The concept of disposability expresses an environmental strategy that considers a regulation change on undesirable outputs as a new business opportunity. Firms attempt to improve their unified (operational and environmental) performance by utilizing new technology and/or new management. Considering the two disposability concepts, this study discusses how to measure unified efficiency under managerial disposability and then discusses how to measure environmental efficiency. The proposed uses of DEA can serve as an empirical basis for measuring new economic concepts such as “Scale Damages (SD)”, corresponding to scale economies for undesirable outputs, and “Damages to Scale (DTS)”, corresponding to returns to scale for undesirable outputs.     

The hyperbolic-oriented efficiency measure as a remedy to infeasibility of super efficiency models

The infeasibility problem in traditional super efficiency models has been well established. A generalization of traditional input- or output-oriented super efficiency models, the directional distance function also suffers from infeasibility and related problems. The hyperbolic-oriented efficiency measure provides an alternative to the input-oriented, output-oriented, and directional efficiency measures in super efficiency models and it has the distinct advantage of eliminating the infeasibility problem for positive input/output data. We also show that using a hyperbolic orientation in a super efficiency model allows us to find feasible solutions for certain cases when the requirement for all data to be positive is relaxed. Further we demonstrate the hyperbolic orientated super efficiency method in an outlier detection application. Together, these results establish the use of the hyperbolic orientation in super efficiency analysis as a realistic alternative in practice.     

基于电能节约的E-DEA模型及其应用

按照全要素能源效率的概念,重点考虑电能投入约束,构造了基于电能节约的E-DEA模型,其目标函数为极大化产出比例和电能投入比例之差,约束条件中除考虑一般投入量约束外,还同时强调电能投入径向节约和产出径向增加。根据模型最优解,给出了相应的有效、非有效、弱有效、用电规模收益状态的判断准则,以及相应于不同有效性情况下决策单元的改进。以合肥市通用制造业规上企业所属21个行业为研究对象,从第二次经济普查中选择年均资产、从业人员、电力、非电力能源、二氧化碳排量为投入指标,主营业务收入为产出指标,对行业电能利用效率进行实证分析,通过分析潜在电能可节约量和主营业务收入可增加量,明确了各行业改进目标。     

Linear programming solutions and distance functions under a constant returns to scale technology

In this paper, we investigate the various relationships among the linear programming solutions of data envelopment analysis (DEA) models under a constant returns to scale technology. We derive the analytical relationships among the efficiency measures and the activity variables for four separate models: the input-based, the output-based, the hyperbolic, and the proportional distance functions. We apply our results in order to derive a test of consistency that can be used in assessing the returns to scale among differing DEA models.     

Benchmarking the operating efficiency of Asia container ports

The aim of this paper is to explore the operating efficiency, the scale efficiency targets, and the variability of DEA efficiency estimates of Asian container ports. This study applies data envelopment analysis (DEA) with the traditional DEA model, most productive scale size concept, returns to scale approach, and bootstrap method to assess the operating performance, set scale efficient targets, and determine efficiency rankings of Asian container ports. The results of this study can provide port managers with insights into resource allocation, competitive advantages, as well as optimization of the operating performance. The potential applications and strengths of DEA in assessing the Asian container ports are highlighted.     

Super-efficiency infeasibility and zero data in DEA

Lee et al. (2011) and Chen and Liang (2011) develop a data envelopment analysis (DEA) model to address the infeasibility issue in super-efficiency models. In this paper, we point out that their model is feasible when input data are positive but can be infeasible when some of input is zero. Their model is modified so that the new super-efficiency DEA model is always feasible when data are non-negative. Note that zero data can make the super-efficiency model under constant returns to scale (CRS) infeasible. Our discussion is based upon variable returns to scale (VRS) and can be applied to CRS super-efficiency models.     

Competition strategy and efficiency evaluation for decision making units with fixed-sum outputs

This paper develops a DEA (data envelopment analysis) model to accommodate competition over outputs. In the proposed model, the total output of all decision making units (DMUs) is fixed, and DMUs compete with each other to maximize their self-rated DEA efficiency score. In the presence of competition over outputs, the best-practice frontier deviates from the classical DEA frontier. We also compute the efficiency scores using the proposed fixed sum output DEA (FSODEA) models, and discuss the competition strategy selection rule. The model is illustrated using a hypothetical data set under the constant returns to scale assumption and medal data from the 2000 Sydney Olympics under the variable returns to scale assumption.     

An epsilon-based measure of efficiency in DEA – A third pole of technical efficiency

In DEA, we have two measures of technical efficiency with different characteristics: radial and non-radial. In this paper we compile them into a composite model called “epsilon-based measure (EBM).” For this purpose we introduce two parameters which connect radial and non-radial models. These two parameters are obtained from the newly defined affinity index between inputs or outputs along with principal component analysis on the affinity matrix. Thus, EBM takes into account diversity of input/output data and their relative importance for measuring technical efficiency.     

The relationship between the efficiency of orthopedic wards and the socio-economic status of their patients

The purpose of this paper is to study the effect of the socio-economic status of patients on the efficiency of orthopedic wards in acute hospitals in Israel (20 hospitals), from the viewpoint of the regulator—Israel Ministry of Health. At the first stage, data envelopment analysis is used with two inputs, and three outputs, where one output is undesirable—“number of deaths”—which also reflects the quality of the health services. At the second stage, various nonparametric tests are utilized to test the relationship between the socio-economic status of patients and the efficiency. As by-product DEA provides benchmark analysis, which indicates the peers of each inefficient ward, and the I/O improvements are needed for achieving efficiency. Two versions of DEA were used: the output oriented version (variable returns to scale), and the non-oriented version (Additive). Further analysis provides comparison of the results with other simple efficiency measures. We also compare between the efficiency from the regulator viewpoint and the hospitals’ viewpoint.