随机逆DEA模型的输出估计研究

逆DEA模型讨论了在保持决策单元的效率指数(即最优值)不变的情况下,当输入水平给定时估计输出值.在逆DEA模型的基础上研究了效率指数提高的输出估计,讨论了带有随机因素的情况,将该问题转化成机会约束的线性规划问题,并用数值算例加以说明.     

具有模糊三角要素的机会约束型DEA模型

确定性 DEA是一种数据敏感的评价方法 ,在某些不利情况下 ,数据的轻微变动将极大的影响评价结果 .针对这一不足 ,根据模糊机会约束规划的理论框架 ,基于 C2 R模型 ,建立了具有模糊三角要素的机会约束型 DEA模型 ( FCCPDEA) ,用机会约束来描述这一不确定性 .在 FCCPDEA模型中 ,从令决策者满意的角度出发 ,用决策者期望各决策单元能达到的最大效率 ,即效率基数 ,来代替理想效率 1,使评价更符合现实 .     

带有随机决策单元的广义数据包络分析方法

广义DEA方法是一种相对效率评价方法,解决了决策单元相对于任意参考系(样本单元集)的效率比较问题.在实际中,有时评价标准是确定的,决策单元的生产具有不确定性,有必要在进行生产之前基于确定性样本单元对随机性决策单元进行相对效率评价.为了解决这个问题,研究样本单元为确定值,决策单元为随机变量的广义DEA模型,分别通过期望值和机会约束将随机模型转化为确定性规划,给出决策单元GEDEA有效和GCDEA有效的概念,GEDEA有效与多目标规划Pareto有效关系,以及利用移动因子对决策单元进行有效性排序方法.     

基于CAR-DEA方法的环境效率评价研究

现有环境效率评价的DEA方法没有考虑多维偏好约束问题,即不同决策单元对不同期望产出和不期望产出的偏好不同. 以地区为例,不同地区对GDP、废水和废气赋予的权重偏好各不相同. 在这种情况下,由于各决策单元的偏好约束不同,形成多维偏好约束集,在传统DEA模型中容易出现无可行解现象. 针对这一问题,基于CAR-DEA方法,结合保证域理论,提出一种解决多维偏好约束集问题的环境效率评价模型. 采用中国工业系统的环境效率评价实例对提出的方法进行了分析和说明.     

带有灰色关联-AHP约束锥的DEA模型

通过构建带有灰色关联-AHP约束锥,对DEA模型中指标的权重进行约束.可以在保持带有灰色关联约束锥的DEA模型不同指标重要性不同客观性的基础上,又能体现决策者对各指标的偏好程度.通过算例对比分析了该模型与传统DEA、带有灰色关联约束锥的DEA以及带有AHP约束锥的DEA模型的不同特点.     

灰变量逆DEA模型的初步研究

初步研究了变量为区间灰数的逆DEA模型。变量为区间灰数时,决策单元效率水平保持不变表达为:对决策单元的输入输出值改变前后对应的灰区间效率进行比较,前者大于等于后者与小于等于后者的可信度相等(均等于0.5)。给出了决策单元非DEA有效时,灰区间变量逆DEA模型解存在的充要条件及一般表达式,以及决策单元弱DEA有效时灰变量逆DEA模型的部分解。     

带有熵权-AHP约束锥的DEA模型

在DEA模型中当考虑较多的投入和产出指标时,容易产生决策单元的过度有效性,影响模型的分析效能.因此有相关研究将AHP约束锥引入DEA模型中,不仅有效地限制了DEA模型指标权重的选择自由性,也能更好地将决策者的主观偏好反映在模型中.但引入AHP约束锥产生的主观性会影响到DEA效率评估的客观性.引入熵权法概念,借鉴其客观赋权的思想,将其与AHP约束锥相结合,不仅保留了带有.AHP约束锥的DEA模型的优点,也中和了AHP约束锥的主观性,保证了DEA模型的相对客观性.     

基于复合DEA模型高校办学效益评价方法研究

传统DEA只能在固定投入(或产出)的情况下,将产出(或投入)尽量扩大(或缩小),而造成决策单元非DEA有效的原因,既有投入方面的因素,也有产出方面的因素,是由投入和产出两方面的原因共同造成的,而不仅仅是一方面的原因.本文考虑投入和产出两方面的因素,构造了复合DEA模型,并研究了基于复合DEA模型高校办学效益评价方法.     

矩阵广义逆硬阈值追踪算法与稀疏恢复问题

本文通过引入支撑集捕获基数及MP广义逆,提出了一种用于稀疏恢复问题的矩阵广义逆硬阈值追踪算法,并在观测误差存在的情况下给出了算法在约束等距条件(RIP)下的收敛性.数值实验表明,算法不仅极大地减少了收敛所需迭代次数,且观测误差存在的情况下稀疏恢复是强健的.     

带有因子约束锥的DEA模型

传统DEA模型将输入输出指标对评价结果的影响等同看待,与实际情况不符.学者们不断尝试运用各种方法对DEA模型中指标的权重进行约束,以体现不同指标重要性的不同.但是,目前的相关研究大多采用主观评价方法,这样会破坏DEA的客观性,而采用因子分析确定的权重是客观的,所以在DEA模型中建立因子约束锥,对权重进行约束,可以在保持DEA客观性不变的基础上体现不同指标重要性的不同.     

Dominance stochastic models in data envelopment analysis

In this paper stochastic models in data envelopment analysis (DEA) are developed by taking into account the possibility of random variations in input-output data, and dominance structures on the DEA envelopment side are used to incorporate the modelbuilder's preferences and to discriminate efficiencies among decision making units (DMUs). The efficiency measure for a DMU is defined via joint dominantly probabilistic comparisons of inputs and outputs with other DMUs and can be characterized by solving a chance constrained programming problem. Deterministic equivalents are obtained for multivariate symmetric random errors and for a single random factor in the production relationships. The goal programming technique is utilized in deriving linear deterministic equivalents and their dual forms. The relationship between the general stochastic DEA models and the conventional DEA models is also discussed.     

An input relaxation measure of efficiency in stochastic data envelopment analysis

We introduce stochastic version of an input relaxation model in data envelopment analysis (DEA). The input relaxation model, recently developed in DEA, is useful to resource management [e.g. G.R. Jahanshahloo, M. Khodabakhshi, Suitable combination of inputs for improving outputs in DEA with determining input congestion, Appl. Math. Comput. 151(1) (2004) 263–273]. This model allows more changes in the input combinations of decision making units than those in the observed inputs of evaluating decision making units. Using this extra flexibility in input combinations we can find better outputs. We obtain a non-linear deterministic equivalent to this stochastic model. It is shown that under fairly general conditions this non-linear model can be replaced by an ordinary deterministic DEA model. The model is illustrated using a real data set.     

An MOLP based procedure for finding efficient units in DEA models

In this paper a multiple objective linear programming (MOLP) problem whose feasible region is the production possibility set with variable returns to scale is proposed. By solving this MOLP problem by multicriterion simplex method, the extreme efficient Pareto points can be obtained. Then the extreme efficient units in data envelopment analysis (DEA) with variable returns to scale, considering the specified theorems and conditions, can be obtained. Therefore, by solving the proposed MOLP problem, the non-dominant units in DEA can be found. Finally, a numerical example is provided.     

DEA models for resource reallocation and production input/output estimation

This paper discusses the “inverse” data envelopment analysis (DEA) problem with preference cone constraints. An inverse DEA model can be used for a decision making unit (DMU) to estimate its input/output levels when some or all of its input/output entities are revised, given its current DEA efficiency level. The extension of introducing additional preference cones to the previously developed inverse DEA model allows the decision makers to incorporate their preferences or important policies over inputs/outputs into the production analysis and resource allocation process. We provide the properties of the inverse DEA problem through a discussion of its related multi-objective and weighted sum single-objective programming problems. Numerical examples are presented to illustrate the application procedure of our extended inverse DEA model. In particular, we demonstrate how to apply the model to the case of a local home electrical appliance group company for its resource reallocation decisions.     

Stochastic models and variable returns to scales in data envelopment analysis

Stochastic Data Envelopment Analysis (DEA) models were developed by taking random disturbances into account for the possibility of variations in input-output data structure. The stochastic efficiency measure of a Decision Making Unit (DMU) is defined via joint probabilistic comparisons of inputs and outputs with other DMUs, and can be characterized by solving a chance constrained programming problem. Deterministic equivalents are derived for both situations of multivariate symmetric random disturbances and a single random factor in the production relationships. An analysis of stochastic variable returns to scale is developed.     

DEA models for ratio data: Convexity consideration

Data envelopment analysis (DEA) is defined based on observed units and by finding the distance of each unit to the border of estimated production possibility set (PPS). The convexity is one of the underlying assumptions of the PPS. This paper shows some difficulties of using standard DEA models in the presence of input-ratios and/or output-ratios. The paper defines a new convexity assumption when data includes a ratio variable. Then it proposes a series of modified DEA models which are capable to rectify this problem.     

Relationships between Data Envelopment Analysis and Multicriteria Decision Analysis

We contrast the different approaches of Data Envelopment Analysis (DEA) and Multiple Criteria Decision Making (MCDM) to superficially similar problems. The concepts of efficiency and Pareto optimality in DEA and MCDM are compared, and a link is demonstrated between the ratio efficiency definition in DEA and a distance measure in input–output space based on linear value functions. The problem of weight sensitivity is discussed in terms of value measurement theory, highlighting the assumptions needed during model formulation in order to justify the use of value judgements to constrain weight flexibility in DEA. Finally, we propose a stochastic approach, in which a probability distribution on efficiencies can be derived for each decision making unit, as a basis for comparison.     

Multi-objective stochastic programming for portfolio selection

Generally, in the portfolio selection problem the Decision Maker (DM) considers simultaneously conflicting objectives such as rate of return, liquidity and risk. Multi-objective programming techniques such as goal programming (GP) and compromise programming (CP) are used to choose the portfolio best satisfying the DM’s aspirations and preferences. In this article, we assume that the parameters associated with the objectives are random and normally distributed. We propose a chance constrained compromise programming model (CCCP) as a deterministic transformation to multi-objective stochastic programming portfolio model. CCCP is based on CP and chance constrained programming (CCP) models. The proposed program is illustrated by means of a portfolio selection problem from the Tunisian stock exchange market.     

生产可能集为凸包时的相对有效性评价模型

给出了一个评价决策单元相对有效性的新的DEA模型,它所对应的生产可能集被称为凸包形生产可能集,同时讨论了该模型解的存在性,定义了决策单元技术DEA有效和"上投影"的概念,断定一个决策单元的"上投影"相对于原来的决策单元是技术DEA有效的。最后给出一个应用新模型进行设施农业效率评价的例子。