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.     

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.     

链式网络DEA模型

数据包络分析(DEA)是评价决策单元(DMU)相对有效性的一种工具,现已得到广泛的应用.传统的DEA不考虑系统内部结构,而是将系统作为一个"黑箱"来度量效率.针对多阶段网络结构提出一个新的网络DEA模型—链式网络DEA模型.研究网络决策单元的网络DEA有效性及各个阶段的弱DEA有效性之间的关系,给出了网络DEA有效的充分必要条件.若网络决策单元不是网络DEA有效的,根据模型可以指出系统在哪些阶段是无效的.     

Decomposing technical efficiency and scale elasticity in two-stage network DEA

The constant returns to scale assumption maintained by neoclassical theorists for justifying the black-box structure of production technology in long run does not necessarily allow one to infer that there are no scale benefits available in its sub-technologies. Most of real-life production technologies are multi-stage in nature, and the sources of increasing returns lie in the sub-technologies. It is, therefore, imperative to estimate the scale economies of a firm not only for the network technology but also for the sub-technologies. To accomplish this, two approaches are suggested in this contribution, based on the premise concerning whether a network technology construct considers allocative inefficiency. The first approach, which is ours, makes use of a single network technology for two interdependent sub-technologies. The second approach, which is due to Kao and Hwang (2011), however, assumes complete allocative efficiency by considering two independent sub-technology frontiers, one for each sub-technology. The distinction between these two approaches is important from a policy point of view since the network efficiencies revealed from these two approaches have distinctive causative factors that do not permit them to be used interchangeably.     

Network DEA: A slacks-based measure approach

Traditional DEA models deal with measurements of relative efficiency of DMUs regarding multiple-inputs vs. multiple-outputs. One of the drawbacks of these models is the neglect of intermediate products or linking activities. After pointing out needs for inclusion of them to DEA models, we propose a slacks-based network DEA model, called Network SBM, that can deal with intermediate products formally. Using this model we can evaluate divisional efficiencies along with the overall efficiency of decision making units (DMUs).     

具有偏好锥的链式网络DEA模型

对链式网络DEA模型进行推广,将"偏好锥"引入网络DEA模型.针对中间产出重要性以及决策者评价时的偏好,建立带有产出锥和投入锥相应的两阶段生产可能集,对具有"偏好锥"的链式网络DEA模型,证明了决策单元为网络DEA有效的充要条件,给出了网络DEA有效性与各阶段弱DEA有效性的关系.另外,文章结合具体算例说明了偏好锥的变化对效率评价的影响.关于两阶段的模型以及相关结论可以推广到多阶段网络结构.     

Network DEA pitfalls: Divisional efficiency and frontier projection under general network structures

Data envelopment analysis (DEA) is a method for measuring the efficiency of peer decision making units (DMUs). Recently network DEA models been developed to examine the efficiency of DMUs with internal structures. The internal network structures range from a simple two-stage process to a complex system where multiple divisions are linked together with intermediate measures. In general, there are two types of network DEA models. One is developed under the standard multiplier DEA models based upon the DEA ratio efficiency, and the other under the envelopment DEA models based upon production possibility sets. While the multiplier and envelopment DEA models are dual models and equivalent under the standard DEA, such is not necessarily true for the two types of network DEA models. Pitfalls in network DEA are discussed with respect to the determination of divisional efficiency, frontier type, and projections. We point out that the envelopment-based network DEA model should be used for determining the frontier projection for inefficient DMUs while the multiplier-based network DEA model should be used for determining the divisional efficiency. Finally, we demonstrate that under general network structures, the multiplier and envelopment network DEA models are two different approaches. The divisional efficiency obtained from the multiplier network DEA model can be infeasible in the envelopment network DEA model. This indicates that these two types of network DEA models use different concepts of efficiency. We further demonstrate that the envelopment model’s divisional efficiency may actually be the overall efficiency.     

Evolution of bank efficiency in Brazil: A DEA approach

This paper investigates cost, technical and allocative efficiencies for Brazilian banks in the recent period (2000–2007). We use Data Envelopment Analysis (DEA) to compute efficiency scores. Brazilian banks were found to have low levels of economic (cost) efficiency compared to banks in Europe and in the US. For the period with high macroeconomic volatility (2000–2002) the economic inefficiency in Brazilian banks can be attributed mainly to technical inefficiency rather than allocative inefficiency. State-owned banks are significantly more cost efficient than foreign, private domestic and private with foreign participation. There is no evidence of differences in economic efficiency due to type of activity and bank size. These results may provide some useful guidance for financial regulators and bank managers.     

A simplified version of the DEA cost efficiency model

This short paper deals with a current cost efficiency model and decreases the number of its constraints as well as its variables, which leads to a strong reduction in the computational requirements.     

Within-group common weights in DEA: An analysis of power plant efficiency

In many real world applications where DEA is applied, DMUs can often be put into groups, such as those which may be under a single management team. This often means that the multipliers used within a group should be common across that group’s members. The case example examined in this regard is one involving a set of power plants, with each containing a set of power units under a common plant management. We develop a goal-programming model for this setting that seeks to derive such a common-multiplier set. The important feature of this multiplier set is that it minimizes the maximum discrepancy among the within-group scores from their ideal levels.     

Measuring the efficiency of NBA teams: additive efficiency decomposition in two-stage DEA

This paper evaluates the efficiency of National Basketball Association (NBA) teams under a two-stage DEA framework. Applying the additive efficiency approach, we decompose overall team efficiency into first-stage wage efficiency and second-stage on-court efficiency and find out the individual endogenous weights for each stage. The empirical results show that NBA teams present a better performance on wage efficiency than for on-court efficiency, as on-court efficiency is influenced by many uncontrollable factors. Moreover, NBA teams, on average, tend to possess a higher weight on the first stage, suggesting that teams’ managers can enhance organizational efficiency more efficaciously by prudentially recruiting players.     

Nested decomposition of multistage nonlinear programs with recourse

Nested decomposition is extended to the case of arborescent nonlinear programs. Duals of extensive forms of nonlinear multistage stochastic programs constitute a particular class of those problems; the method is tested on a set of problems of that type.     

具有偏好锥的面向输出的超效率DEA模型分析

鉴于传统DEA模型无法区分有效决策单元,超效率DEA模型未考虑决策者的偏好,现提出面向输出的权重受限的综合超效率DEA模型及其投影概念,并讨论该模型与其他超效率DEA模型之间的关系.接着,分析模型的最优目标函数值与决策单元有效性之间的关系,并讨论面向输出的权重受限的综合超效投影与多目标规划问题的非支配解之间的关系.最后,通过对中国西部12个地区工业企业科技创新效率综合评价,并与原有方法进行比较研究,得出本文方法更具优势和合理性.     

Bridging radial and non-radial measures of efficiency in DEA

Data envelopment analysis (DEA) has been utilized worldwide for measuring efficiencies of banks, telecommunications, electric utilities and so forth. Yet, the existing models have some well-known shortcomings that limit their usefulness. In DEA we have two fundamental approaches to measuring efficiency with very different characteristics; radial and non-radial. We demonstrate a method for linking these two approaches in a unified framework called Connected-SBM (slacks-based measure). It includes two scalar parameters, and by changing the parameter values we can relocate the analysis anywhere between the radial and the non-radial models. An appropriate choice of these parameters can overcome the key shortcomings inherent in the two approaches, namely, proportionality and mixed patterns of slacks.     

Measuring overall efficiency and effectiveness using DEA

This paper presents a framework where data envelopment analysis (DEA) is used to measure overall efficiency and show how to apply this framework to assess effectiveness for more general behavioral goals. The relationships between various cone-ratio DEA models and models to measure overall efficiency are clarified. Specifically it is shown that as multiplier cones tighten, the cone-ratio DEA models converge to measures of overall efficiency. Furthermore, it is argued that multiplier cone and cone-ratio model selection must be consistent with the behavioral goals assigned or assumed for purposes of analysis. Consistent with this reasoning, two new models are introduced to measure effectiveness when value measures are represented by separable or linked cones, where the latter can be used to analyze profit-maximizing effectiveness.     

Duality,efficiency computations and interpretations in imprecise DEA

Data envelopment analysis (DEA) has proven to be a useful tool for assessing efficiency or productivity of organizations which is of vital practical importance in managerial decision making. While DEA assumes exact input and output data, the development of imprecise DEA (IDEA) broadens the scope of applications to efficiency evaluations involving imprecise information which implies various forms of ordinal and bounded data possibly or often occurring in practice. The primary purpose of this article is to characterize the variable efficiency in IDEA. Since DEA describes a pair of primal and dual models, also called envelopment and multiplier models, we can basically consider two IDEA models: One incorporates imprecise data into envelopment model and the other includes the same imprecise data in multiplier model. The issues of rising importance are thus the relationships between the two models and how to solve them. The groundwork we will make includes a duality study, which makes it possible to characterize the efficiency solutions from the two models and link with the efficiency bounds and classifications that some of the published IDEA studies have done. The other purposes are to present computational aspects of the efficiency bounds and how to interpret the efficiency solutions. The computational method developed here extends the previous IDEA method to effectively incorporate a more general form of strict ordinal data and partial orders in its framework, which in turn overcomes some drawbacks of the previous approaches. The interpretation of the resulting efficiency is also important but we have never seen it before.     

DEA models for supply chain efficiency evaluation

An appropriate performance measurement system is an important requirement for the effective management of a supply chain. Two hurdles are present in measuring the performance of a supply chain and its members. One is the existence of multiple measures that characterize the performance of chain members, and for which data must be acquired; the other is the existence of conflicts between the members of the chain with respect to specific measures. Conventional data envelopment analysis (DEA) cannot be employed directly to measure the performance of supply chain and its members, because of the existence of the intermediate measures connecting the supply chain members. In this paper it is shown that a supply chain can be deemed as efficient while its members may be inefficient in DEA-terms. The current study develops several DEA-based approaches for characterizing and measuring supply chain efficiency when intermediate measures are incorporated into the performance evaluation. The models are illustrated in a seller-buyer supply chain context, when the relationship between the seller and buyer is treated first as one of leader-follower, and second as one that is cooperative. In the leader-follower structure, the leader is first evaluated, and then the follower is evaluated using information related to the leader's efficiency. In the cooperative structure, the joint efficiency which is modelled as the average of the seller's and buyer's efficiency scores is maximized, and both supply chain members are evaluated simultaneously. Non-linear programming problems are developed to solve these new supply chain efficiency models. It is shown that these DEA-based non-linear programs can be treated as parametric linear programming problems, and best solutions can be obtained via a heuristic technique. The approaches are demonstrated with a numerical example.     

Pesticide use,environmental spillovers and efficiency: A DEA risk-adjusted efficiency approach applied to Dutch arable farming

Pesticides are widely used by crop producers in developed countries to combat risk associated with pests and diseases. However, their indiscriminate use can lead to various environmental spillovers that may alter the agricultural production environment thus contributing to production risk. This study utilises a data envelopment analysis (DEA) approach to measure performance of arable farms, incorporating pesticides’ environmental spillovers and output variance as undesirable outputs in the efficiency analysis and taking explicitly into account the effect of pesticides and other inputs on production risk. The application focuses on panel data from Dutch arable farms over the period 2003–2007. A moment approach is used to compute output variance, providing empirical representations of the risk-increasing or -decreasing nature of the used inputs. Finally, shadow values of risk-adjusted inputs are computed. We find that pesticides are overused in Dutch arable farming and there is a considerable evidence of the need for decreasing pesticides’ environmental spillovers.     

A general cone decomposition theory based on efficiency

LetK ₁ andK ₂ be two convex cones in some common vector space. This paper is concerned with the question of finding a good decomposition, with respect toK ₁ andK ₂, of a given element of the Minkowski sumK ₁ +K ₂. We propose the criterion of efficiency as a measure for the quality of a decomposition. This criterion allows us to set up a framework from which a general cone decomposition theory is then derived.Research supported by Dirección General de Investigación Científica y Técnica (DGICYT), under project PS89-0058.     

Identifying the efficiency status in network DEA

Data envelopment analysis (DEA) is commonly employed to evaluate the efficiency performance of a decision making unit (DMU) that transforms exogenous inputs into final outputs. In such a black-box DEA approach, details of an internal production process of the DMU are typically ignored and hence the locations of inefficiency are not adequately provided. In view of this, DEA researchers have recently developed various network approaches by looking into the black box, where the inputs that enter the box and the outputs that come out of it are only considered. However, most of these network approaches evaluate divisional efficiency by using an optimal solution of their respective optimization problem. If such an optimal solution is used in the case when there are multiple optima, then managerial guidance based on this solution alone may be inappropriate because more appropriate targets from the viewpoint of management may be ignored. Taking this fact into account, therefore, we propose a network approach for identifying the efficiency status of each DMU and its divisions. This approach provides a practical computational procedure.