Multi-valued measures in DEA in the presence of undesirable outputs

Data envelopment analysis (DEA) evaluates the relative efficiency of a set of comparable decision making units (DMUs) with multiple performance measures (inputs and outputs). Classical DEA models rely on the assumption that each DMU can improve its performance by increasing its current output level and decreasing its current input levels. However, undesirable outputs (like wastes and pollutants) may often be produced together with desirable outputs in final products which have to be minimized. On the other hands, in some real-world situations, we may encounter some specific performance measures with more than one value which are measured by various standards. In this study, we referee such measures as multi-valued measures which only one of their values should be selected. For instance, unemployment rate is a multi-valued measure in economic applications since there are several definitions or standards to measure it. As a result, selecting a suitable value for a multi-valued measure is a challenging issue and is crucial for successful application of DEA. The aim of this study is to accommodate multi-valued measures in the presence of undesirable outputs. In doing so, we formulate two individual and summative selecting directional distance models and develop a pair of multiplier- and envelopment-based selecting approaches. Finally, we elaborate applicability of the proposed method using a real data on 183 NUTS 2 regions in 23 selected EU-28 countries.     

A new slacks-based measure of Malmquist–Luenberger index in the presence of undesirable outputs

In the majority of production processes, noticeable amounts of bad byproducts or bad outputs are produced. The negative effects of the bad outputs on efficiency cannot be handled by the standard Malmquist index to measure productivity change over time. Toward this end, the Malmquist–Luenberger index (MLI) has been introduced, when undesirable outputs are present. In this paper, we introduce a Data Envelopment Analysis (DEA) model as well as an algorithm, which can successfully eliminate a common infeasibility problem encountered in MLI mixed period problems. This model incorporates the best endogenous direction amongst all other possible directions to increase desirable output and decrease the undesirable outputs at the same time. A simple example used to illustrate the new algorithm and a real application of steam power plants is used to show the applicability of the proposed model.     

Duality of weakly disposable technology

The axiom of weak disposability is frequently imposed in data envelopment analysis (DEA) models involving undesirable outputs such as pollution. This paper sheds new light on the economic interpretation of weak disposability by developing dual formulations of the weakly disposable DEA technology. We find that the economic implications of weak disposability on the multiplier DEA problem are two-fold: (1) the shadow prices of the undesirable outputs can be positive or negative, and (2) the economic loss of the benchmark cannot exceed the suck cost of the inputs. We interpret the second implications as a limited liability condition. The dual formulations developed in this paper enable one to estimate shadow prices of the undesirable outputs using the weakly disposable technology. The insights gained are illustrated by a numerical example and an empirical application to the US power plants.     

环保项目有效性评价的数据包络分析方法

利用数据包络分析(DEA)方法评价环保项目有效性时,输入、输出数据中可能同时存在环境因素,不符合传统的DEA模型要求,需要对这些数据进行转换。本文讨论了"不好的"数据平移转换法、输入和输出因素转换法、倒数转换法,建立了三种DEA模型,对建立的DEA模型一致性进行了分析,拓宽了以前DEA模型的应用范围。一个例子验证了这三种方法在评价环保项目有效性时是一致的。     

存在非期望输入输出的多阶段系统效率评价模型

现有多阶段DEA模型的研究普遍假设所有输入、输出均为期望指标, 对存在非期望指标的情况研究较少, 尚无对最初投入和中间产出带有非期望指标的研究。为此, 本文首先提出了输入、输出类型的判定方法, 并将其应用于存在非期望输入、输出的两阶段系统。进一步针对存在非期望指标的两阶段生产系统中同种输入、输出, 尤其中间产出类型判定一致与不一致的情况, 构建了相应的生产可能集以及两阶段DEA模型, 最后利用本文方法和模型对我国上市银行效率进行了评价。     

Two-stage DEA models with undesirable input-intermediate-outputs

Data envelopment analysis (DEA) is a non-parametric approach for measuring the relative efficiencies of peer decision making units (DMUs). Many studies have examined DEA efficiencies of two-stage systems, where all the outputs from the first stage are the only inputs to the second stage. Although single-stage DEA models with undesirable input-outputs have been extensively studied, there still lacks of more systematical investigation on two-stage DEA with undesirable variables. For instance, depending on its operating model, even whether an intermediate variable is desirable or undesirable can be questionable for a particular two-stage system. Furthermore, most of the existing studies on two-stage systems focus on the case where only the final outputs are undesirable. In this work, we try to systematically examine two-stage DEA models with undesirable input-intermediate-outputs. Particularly, we utilize the free-disposal axioms to construct the production possibility sets (PPS) and the corresponding DEA models with undesirable variables. The proposed models are then used to illustrate some theoretical perspectives by using the data of China׳s listed banks.     

Evolving the latent variable model as an environmental DEA technology

This article tests several nonparametric DEA models for their ability to accurately decompose CO₂ emissions change using a Malmquist styled decomposition framework. This production oriented activity analysis involves panel data and two data sets from the literature for comparison. A new Latent Variable radial input-oriented technology is introduced that is closely associated with a Koopmans Efficient Slacks Based Model. The Latent Variable technology simultaneously reduces inputs and undesirable outputs in a single Multiple Objective Linear Program. This production theoretic methodology is adapted to preserve both scale efficiency and causality within the envelopment framework. Finally, the application studies demonstrate the internal consistency of the Latent Variable reduction coefficients, which overturns previous results and paves the way for further research into undesirable externalities.     

The enhanced Russell-based directional distance measure with undesirable outputs: Numerical example considering CO2 emissions

Following the spirit of the enhanced Russell graph measure, this paper proposes an enhanced Russell-based directional distance measure (ERBDDM) model for dealing with desirable and undesirable outputs in data envelopment analysis (DEA) and allowing some inputs and outputs to be zero. The proposed method is analogous to the output oriented slacks-based measure (OSBM) and directional output distance function approach because it allows the expansion of desirable outputs and the contraction of undesirable outputs. The ERBDDM is superior to the OSBM model and traditional approach since it is not only able to identify all the inefficiency slacks just as the latter, but also avoids the misperception and misspecification of the former, which fails to identify null-jointness production of goods and bads. The paper also imposes a strong complementary slackness condition on the ERBDDM model to deal with the occurrence of multiple projections. Furthermore, we use the Penn Table data to help us explore our new approach in the context of environmental policy evaluations and guidance for performance improvements in 111 countries.     

An integrated environmental risk assessment framework for coal-fired power plants: A fuzzy logic approach

This study quantifies the environmental risk of a coal-fired thermal power plant during operation by using environmental monitoring data, site surveys, and documented evidence. The following criteria are assessed: emissions (CO, SO₂, NO_x, PM₁₀), impact on aquatic ecosystem (fish protection at cooling water intake and cooling water discharge temperature), and waste management (fly ash and bottom ash). Fuzzy sets were defined for each criterion, taking environmental regulatory context as an expert judgment. A survey was conducted with multiple stakeholders to determine the relative importance of risk factors. The survey results showed that the most concerned risks are SO₂ and NO_x emissions. The proposed method estimates the risk of each environmental criterion separately and then accumulates them into an environmental risk index (ERI). Accordingly, we assessed the Catalagzi coal-fired power plant, which has been in operation on the Black Sea coast in northwestern Turkey. For this case study, the ERI resulted in a value of 0.78 (on a scale of 0–1), showing high environmental risk to the facility. Moreover, the applicability of the proposed framework was tested in several existing coal-fired power plants using simultaneous measurements. All studied coal-fired power plants in Turkey have unacceptable pollutants (PM₁₀, SO₂, and NO_x) concentration levels indicating high health risk potential. The application of the integrated environmental risk assessment framework showed that new environmental regulations are needed in Turkey to specify more strict emission limits and to monitor CO₂, fine particulate matter emissions, cooling water discharge, and fish protection at cooling water intake.     

Slacks-based inefficiency approach for general networks with bad outputs: An application to the banking sector

In this paper the efficiency assessment of general networks of processes that produce both desirable and undesirable outputs is addressed. This problem arises in many contexts (e.g. transportation, energy generation, etc.). A general networks slacks-based inefficiency (GNSBI) measure can be computed using a simple linear program that takes into account the weak disposability of the bad outputs. The slacks-based inefficiency (SBI) of each process is also calculated. Target values for all inputs, outputs (both desirable and undesirable) and even intermediate products are also provided. The proposed approach is rather general and can accommodate many different network topologies and returns to scale assumptions. Two applications to the banking sector are presented: one to assess banks efficiencies and another to assess bank branches.     

Eco-efficiency analysis of paper mills along the Huai River: An extended DEA approach

The objective of this paper is to estimate the ecological efficiency of paper mills along the Huai River in China. The main characteristic of the ecological efficiency evaluation problem is that an undesirable output of biochemical oxygen demand (BOD) and a non-discretionary input (BOD emission quota) should be considered simultaneously. By analyzing the impacts of the non-discretionary input on decision-making units’ (DMUs) desirable and undesirable outputs, a non-radial output-oriented DEA model is proposed. In the proposed model, we describe a new approach of defining reference set that requires reference units operate in a similar environment on average. We employ the model to provide efficient inputs/outputs targets for DMU managers to improve DMUs’ efficiencies. Based on the developed model, impacts of the non-discretionary input on DMUs’ returns are also analyzed. We illustrate the proposed model, using real data, for 32 paper mills along the Huai River in China.     

Dynamic DEA: A slacks-based measure approach

In data envelopment analysis, there are several methods for measuring efficiency changes over time, e.g. the window analysis and the Malmquist index. However, they usually neglect carry-over activities between two consecutive terms and only focus on the separate time period independently aiming local optimization in a single period, even if these models can take into account the time change effect. In the actual business world, a long time planning and investment is a subject of great concern. For these cases, single period optimization model is not suitable for performance evaluation. To cope with long time point of view, the dynamic DEA model incorporates carry-over activities into the model and enables us to measure period specific efficiency based on the long time optimization during the whole period. Dynamic DEA model proposed by Färe and Grosskopf is the first innovative contribution for such purpose. In this paper we develop their model in the slacks-based measure (SBM) framework, called dynamic SBM (DSBM). The SBM model is non-radial and can deal with inputs/outputs individually, contrary to the radial approaches that assume proportional changes in inputs/outputs. Furthermore, according to the characteristics of carry-overs, we classify them into four categories, i.e. desirable, undesirable, free and fixed. Desirable carry-overs correspond, for example, to profit carried forward and net earned surplus carried to the next term, while undesirable carry-overs include, for example, loss carried forward, bad debt and dead stock. Free and fixed carry-overs indicate, respectively, discretionary and non-discretionary ones. We develop dynamic SBM models that can evaluate the overall efficiency of decision making units for the whole terms as well as the term efficiencies.     

Time-staged outputs in DEA

This paper examines the issue of handling outputs in DEA that occur at different stages in time. As a backdrop for the research we examine a data set involving the evaluation of efficiencies of business schools. The data focuses explicitly on a particular institution, namely the business school ENCSH (Escuela de Negocios, Ciencias Sociales y Humanidades) at ITESM (Instituto Tecnologico y de Estudios Superiores Monterrey) in Mexico. This school of business is evaluated relative to 41 peer institutions in the USA, using data envelopment analysis as the principal evaluation instrument. Using internships and jobs as outputs, and various quality measures as inputs, we demonstrate that this problem setting gives rise to the phenomenon of time-staged outputs. Specifically, the two outputs occur at different points in time, meaning that one of them plays a dual role. While this problem might potentially be viewed as a type of network DEA model, we demonstrate that a modification of the conventional DEA methodology is a more appropriate structure to handle this situation.     

具有双重角色和非期望要素的供应商评价两阶段DEA模型

在基于DEA方法的供应商评价过程中,会出现供应商同时具有双重角色要素和非期望输出要素的情形。文章提出了一个处理双重角色要素的新思路,认为DEA模型中双重角色要素同时扮演了输入和输出两个角色,所有双重角色要素本质上就是网络DEA模型中的中间变量,并同时认为包含双重角色要素的生产系统一定能分解成为多个子系统,其中的双重角色要素既是一个子系统的输入,同时又是另一个子系统的输出。为测度供应商的效率,基于已有关系型两阶段DEA模型,将供应商的生产运营视为两阶段过程,其双重角色要素视为两阶段过程的中间变量,并通过将所有输出以加权和的形式表达,但对非期望输出用负的权重的方式,提出了一个具有双重角色和非期望输出要素的供应商评价两阶段DEA模型,最后用一个实例验证了方法的可行。     

Turbofan aero-engine efficiency evaluation: An integrated approach using VSBM two-stage network DEA

The application of Data Envelopment Analysis (DEA) has been wide, especially for the purpose of evaluating efficiency among similar production processes within enterprises belonging to particular industries. Although research pertinent to DEA has primarily focused on efficiency of production systems or corporate entities/organizations (e.g., terminals, hospitals, universities/schools, banks), fairly little attention has been given to efficiency evaluation among engineering systems featuring common configurations (e.g., automobiles, power plants). Furthermore, the limited previous literature involving efficiency evaluation of engineering systems has implemented DEA methodologies with limited discriminative power, i.e. there is a quite increased portion of efficient Decision Making Units (DMUs). In the current paper, a methodological framework deploying Variable intermediate measures Slacks-Based Measure (VSBM) Two-Stage Network DEA is implemented, in order to evaluate the efficiency of turbofan aero-engines, currently utilized by active-duty commercial and military aircraft. Apart from exploring the positive correlation of DEA efficiency with engineering efficiency, we also develop a methodology evaluating the features of near-future turbofan designs in terms of DEA efficiency, thus comprising a potential tool for efficiency assessment of any turbofan aero-engine being in the conceptual or preliminary design stage.     

Dynamic performance assessment of bus transit with the multi-activity network structure

This paper proposes a multi-activity dynamic network data envelopment analysis model that combines the multi-activity, network and dynamic DEA models to assess the performance in terms of individual activities, individual processes, individual periods and overall operation. The main advantage of this model is that the linkages among activities and processes, the shared inputs among activities and processes, and the carry-over items among periods are included in a unified model. It can provide more appropriate performance measures. An empirical application of 20 bus transit firms in Taiwan for the period 2004–2012 is provided. Based on the operational characteristics of bus transit firms, both desirable and undesirable outputs are also incorporated into this model. The results show that none of the bus transit firms was effective in terms of the operational effectiveness, and the sources of operational ineffectiveness among bus transit firms were different. Over the period 2004–2012, the period-operational effectiveness scores maintained stable variance, the period efficiencies of highway and urban bus services appeared to have similar patterns, and transit bus firms performed well in the consumption process.     

多层次结构DEA模型及其应用

在评价实践中,评价者通常倾向采用一组指标或指标体系对DMUs展开相对全面的评价,不同层次指标的重要性也往往不同。然而,标准DEA模型在DMUs有限条件下经常会面临无法直接处理过多的评价指标,也无法直接处理多层次指标的问题。本文从DEA模型中的序结构和测度出发,构建了符合多层次指标体系特点,能相对全面地体现评价者价值导向,且具有合理区分能力的多层次结构DEA模型,并以15个机构基础研究的投入-产出评价为例展开了应用分析。     

存在非期望产出的决策单元阻塞问题研究

阻塞是指企业的过量投入引起生产效益下降的经济现象,近年来已经受到实业界与学术界的广泛关注。现有的决策单元阻塞问题研究普遍假设产出均是期望指标,然而,在实际生产中很多产出属于非期望指标。本文构建了同时存在期望产出和非期望产出决策单元的阻塞度量模型,该模型不仅可以判别决策单元是否存在阻塞,而且可以测算各项投入的阻塞程度,并给出了决策单元阻塞和技术无效之间的关系。最后,运用所提出的模型对我国上市商业银行的效率和阻塞情况进行了测算与分析,验证了本文模型的实用性与可行性。     

考虑碳价下限的燃煤发电碳减排投资及其政策分析

燃煤发电是电力供应保障的重要基础,也是二氧化碳排放的主要来源之一。论文针对碳排放权价格（碳价）、燃煤发电商上网电量以及碳减排设施的单位运维成本都随机波动的情况,构建考虑碳价下限的燃煤发电商碳减排投资实物期权模型,在模型求解基础上,针对某60万千瓦燃煤发电机组,通过数值仿真方法,考察碳价下限对碳减排预期投资时间的影响,并探讨碳价初值、碳减排单位运维成本初值如何影响碳价下限政策的有效性,比较碳价下限与直接投资补贴政策的优劣,分析结果表明：（1）碳价下限政策可能会激励燃煤发电商提早进行碳减排投资,但提高碳价下限不一定能降低碳减排投资阈值;（2）碳价下限政策实施的有效区域由碳价初值、碳减排单位运维成本初值等参数有关,在该有效区域内,通过碳价下限的调整可调节碳减排投资的预期时间;（3）相对于直接投资补贴政策,碳价下限能显著节省补贴资金。     

基于分段参数型DEA前沿面的投入—产出型技术效率

由传统DEA模型可以直接测算投入固定(产出固定)的条件下,面向产出(投入)的技术效率。尽管加型DEA模型同时考虑了投入和产出的松弛,但却不能像传统模型一样直接测算投入—产出型技术效率。为了直接由加性模型测算投入产出型技术效率,本文将利用DEA有效决策单元建立分段参数型DEA生产前沿面,并根据古典技术效率的定义,解决投入产出型技术效率的测算问题。研究发现,这种效率实质上是产出型技术效率与投入配置效率的乘积。由于同时考虑了投入和产出的技术无效性,与其它类型的技术效率相比,这种投入产出型技术效率的可分性更强。