一种基于偏好分布的群决策方法

为了满足群决策的实际需求,本文提出了一种基于偏好分布的群决策方法,该方法利用完全不对称预先排序向量表示决策者的偏好,通过分析计算偏好排序向量的密度和分布结构,从可行方案集合中寻找所有决策者都能接受的优选方案集合,逐次缩小搜索空间以逼近一致满意解。该方法结合冲突分析,可进一步分析决策者之间的相互关系,集成于谈判支持系统,具有直观、实用等特点,最后给出了一个实际例子说明该方法。     

FAIRNESS IN COST ALLOCATIONS AND COOPERATIVE GAMES

In an economic environment where there is a conflict of interest among several parties, the job of an adjudicator is to devise a “solution” to this conflict that is “fair” or at least acceptable to all parties. For example, a cost accountant may have to allocate the cost of a research and development division or of a common power facility to several departments—each of which makes some use of the facility. Perhaps, several firms responsible for the pollution of a lake or river may be under a court order to clean up the lake, and he must decide how to distribute this cost among the several firms. The purpose of this paper is to illustrate through the above two examples how the theory of cooperative games may be of service to such an adjudicator. However, there are several different notions of “fairness,” and the decision as to which notion of “fairness” is appropriate to which conflict situation is a decision that at this point is beyond the theory of cooperative games. By examining these different notions of fairness, a person may find himself able to distinguish features of various solution proposals which make one solution “fairer” than another.     

Community Resilience and Decision Theory Challenges for Catastrophic Events

Extreme and catastrophic events pose challenges for normative models of risk management decision making. They invite development of new methods and principles to complement existing normative decision and risk analysis. Because such events are rare, it is difficult to learn about them from experience. They can prompt both too little concern before the fact, and too much after. Emotionally charged and vivid outcomes promote probability neglect and distort risk perceptions. Aversion to acting on uncertain probabilities saps precautionary action; moral hazard distorts incentives to take care; imperfect learning and social adaptation (e.g., herd‐following, group‐think) complicate forecasting and coordination of individual behaviors and undermine prediction, preparation, and insurance of catastrophic events. Such difficulties raise substantial challenges for normative decision theories prescribing how catastrophe risks should be managed. This article summarizes challenges for catastrophic hazards with uncertain or unpredictable frequencies and severities, hard‐to‐envision and incompletely described decision alternatives and consequences, and individual responses that influence each other. Conceptual models and examples clarify where and why new methods are needed to complement traditional normative decision theories for individuals and groups. For example, prospective and retrospective preferences for risk management alternatives may conflict; procedures for combining individual beliefs or preferences can produce collective decisions that no one favors; and individual choices or behaviors in preparing for possible disasters may have no equilibrium. Recent ideas for building “disaster‐resilient” communities can complement traditional normative decision theories, helping to meet the practical need for better ways to manage risks of extreme and catastrophic events.     

A deterministic model for the housing decision

The decision to rent or buy housing, or to choose among various housing acquisition alternatives, represents an important and complex financial problem, which confronts virtually all individuals. This paper develops a comprehensive model (within the institutional and legislative context of the United States) which provides theoretically appropriate criteria for evaluating personal housing alternatives. Empirical results clearly indicate the economic consequences of housing alternatives, and both substantiate some and contradict other “wisdoms” concerning the housing decision.     

1 network privatisation: The trend for the future

At the recent Financial Times Conference on Telecommunications and the European Business Market: the Perspectives for Change, two of the contributors examined the question of whether companies should “make” their own private telecommunications network, or “buy” a publicly-offered service.The topic is not only interesting as a case study of “make or buy”, but is especially timely in the specific field of telecommunications in Europe. In June 1987, the European Commission issued its Green Paper on telecommunications liberalisation and rationalisation of Europe's equipment manufacturers. Current difficulties include national regulatory powers, cross subsidies, lack of common standards, and lack of agreement on standards, frequencies and tariff principles. Not least, rapid changes in the technology itself has turned telecommunications into a Strategic competitive asset for companies.The two authors of these articles argue from slightly different perspectives; White as a major user developing into a provider, and Wilson as an adviser and provider. Both are convinced that the make or buy decision is an over-simplification; there are other, intermediate, options. Both agree that which ever decision is taken, it is likely to be the most important one in information technology that companies make in the next few years.     

Branch‐and‐Price Methods for Prescribing Profitable Upgrades of High‐Technology Products with Stochastic Demands*

This paper develops a model that can be used as a decision support aid, helping manufacturers make profitable decisions in upgrading the features of a family of high‐technology products over its life cycle. The model integrates various organizations in the enterprise: product design, marketing, manufacturing, production planning, and supply chain management. Customer demand is assumed random and this uncertainty is addressed using scenario analysis. A branch‐and‐price (B&P) solution approach is devised to optimize the stochastic problem effectively. Sets of random instances are generated to evaluate the effectiveness of our solution approach in comparison with that of commercial software on the basis of run time. Computational results indicate that our approach outperforms commercial software on all of our test problems and is capable of solving practical problems in reasonable run time. We present several examples to demonstrate how managers can use our models to answer “what if” questions.     

A DECISION—RULE TECHNIQUE FOR PREDICTING ACADEMIC SUCCESS

The objective of this paper is to illustrate an application of a quantitative decision-rule strategy which incorporates the Wald classification statistic. An empirical example of this classification technique using data obtained from The University of Texas at Austin Measurement and Evaluation Center is presented. This study originated as an attempt to illustrate the usefulness of this infrequently used statistical technique as a practical tool for “predicting” academic performance. A method for measuring the operational effectiveness of the decision-rule used is also illustrated. This study emphasizes classification as an important part of statistical analysis and focuses on the Wald classification statistic to illustrate one type of problem for which it is suitable.     

The Value of Environmental Information without Control of Subsequent Decisions

The standard value of information approach of decision analysis assumes that the individual or agency that collects the information is also in control of the subsequent decisions based on the information. We refer to this situation as the “value of information with control (VOI‐C).” This paradigm leads to powerful results, for example, that the value of information cannot be negative and that it is zero, when the information cannot change subsequent decisions. In many real world situations, however, the agency collecting the information is different from the one that makes the decision on the basis of that information. For example, an environmental research group may contemplate to fund a study that can affect an environmental policy decision that is made by a regulatory organization. In this two‐agency formulation, the information‐acquiring agency has to decide, whether an investment in research is worthwhile, while not being in control of the subsequent decision. We refer to this situation as “value of information without control (VOI‐NC).” In this article, we present a framework for the VOI‐NC and illustrate it with an example of a specific problem of determining the value of a research program on the health effects of power‐frequency electromagnetic fields. We first compare the VOI‐C approach with the VOI‐NC approach. We show that the VOI‐NC can be negative, but that with high‐quality research (low probabilities of errors of type I and II) it is positive. We also demonstrate, both in the example and in more general mathematical terms, that the VOI‐NC for environmental studies breaks down into a sum of the VOI‐NC due to the possible reduction of environmental impacts and the VOI‐NC due to the reduction of policy costs, with each component being positive for low environmental impacts and high‐quality research. Interesting results include that the environmental and cost components of the VOI‐NC move in opposite directions as a function of the probability of environmental impacts and that VOI‐NC can be positive, even though the probability of environmental impacts is zero or one.     

Shared Services Transformation: Conceptualization and Valuation from the Perspective of Real Options

In today's volatile global economy, where many organizations face severe pressure to downsize, the “shared services” model, in which a firm merges common functions performed by multiple units into a single service delivery organization, provides an innovative approach to make business more efficient and effective. To successfully implement shared services, firms need to strategically decide whether and how to pursue various service transformation alternatives such as simplification, standardization, consolidation, insourcing, or outsourcing. In this study, we develop the notion of real options into a unique theoretical lens for conceptualizing service organizations and their transformation in an uncertain business environment. Specifically, we view service organization as a set of strategic options that give the firm preferential access to future transformation opportunities. We create a taxonomy of these options, and introduce a decision methodology for valuing alternative shared services transformation approaches. We illustrate this methodology by applying it in a real business case to justify a global firm's decision regarding the transformation of its finance organization.     

基于后悔理论和DEMATEL的语言型多属性决策方法

针对目前语言型多属性决策方法大多基于期望效用理论且不考虑指标间影响关系的不足，提出了一种将后悔理论和决策试验与评价试验法相结合的语言型多属性决策方法。首先，依据后悔理论的思想，定义了语言后悔-欣喜函数，给出了方案感知效用值的计算公式；然后，利用决策试验与评价试验法分析指标间的影响关系，给出了基于语言DEMATEL的指标权重确定方法，再通过指标总容量最大优化模型给出了基于注水原理的指标权重确定方法，并在此基础上求解方案的综合感知效用值，据此对方案进行排序择优；最后，通过两个应用实例来验证所提方法的可行性和有效性。实例结果表明，由于该方法同时考虑了决策者的心理行为和指标间的影响关系，因此可使决策结果更加贴近现实且更为可靠。     

AFFECTIVE RESPONSES WITHIN A COMPLEX DECISION-MAKING TASK: THE INFLUENCE OF “PERCEPTUALLY” ILL-STRUCTURED PROBLEMS

The perceptual effects of varying levels of expert advice for potentially improving on strategic decisions were examined in conjunction with goals. The amounts of advice about decision alternatives, as well as assigned goals ranging from “nearly impossible” to “easy,” were manipulated. The task used was complex and functioned perceptually as an “ill-structured” problem. Mixed results indicated that more advice significantly affected satisfaction but advice in general had little influence on effort. On the other hand, as goal difficulty decreased, satisfaction and effort significantly increased. Easy goals were superior to more difficult ones within this perceptually ill-structured decision-making situation.     

区间概率条件下属性值为不确定语言变量的风险型多属性决策研究

针对区间概率条件下属性值为不确定语言信息且属性权重未知的风险型多属性决策问题,提出了一种基于概率理论和不确定语言变量的TOPSIS决策方法。首先建立了区间概率转化为点概率的数学模型,通过期望值将风险型决策矩阵转化为确定型矩阵;然后利用方案与理想解越近方案越优,与负理想解越远方案越优的原则建立属性权重确定模型,并利用TOPSIS方法的相对优属度大小确定方案的排序;最后通过应用案例说明了本方法的决策步骤。     

Determining causal relationships in leadership research using Machine Learning: The powerful synergy of experiments and data science

Machine Learning (ML) techniques offer exciting new avenues for leadership research. In this paper we discuss how ML techniques can be used to inform predictive and causal models of leadership effects and clarify why both types of model are important for leadership research. We propose combining ML and experimental designs to draw causal inferences by introducing a recently developed technique to isolate “heterogeneous treatment effects.” We provide a step-by-step guide on how to design studies that combine field experiments with the application of ML to establish causal relationships with maximal predictive power. Drawing on examples in the leadership literature, we illustrate how the suggested approach can be applied to examine the impact of, for example, leadership behavior on follower outcomes. We also discuss how ML can be used to advance leadership research from theoretical, methodological and practical perspectives and consider limitations.     

考虑决策者心理行为的混合型随机多属性决策方法

针对混合型随机多属性决策问题,提出一种考虑决策者心理行为的决策分析方法。在该方法中,首先将具有离散型随机变量、灰色型随机变量和语言型变量形式的属性值规范化到区间内;然后将决策者给出的针对不同时期的属性期望视为参照点,并通过计算方案属性值与参照点的距离构建方案的益损矩阵;进一步地,依据累计前景理论,计算方案在不同属性上的收益和损失价值,并在此基础上,通过集结不同属性和不同时期的方案前景值确定各方案的综合前景值,进而依据得到的综合前景值确定方案排序结果。最后,通过一个算例说明了该方法的有效性和可行性。     

Strategic Learning and the Topology of Social Networks

We consider a group of strategic agents who must each repeatedly take one of two possible actions. They learn which of the two actions is preferable from initial private signals and by observing the actions of their neighbors in a social network. We show that the question of whether or not the agents learn efficiently depends on the topology of the social network. In particular, we identify a geometric “egalitarianism” condition on the social network that guarantees learning in infinite networks, or learning with high probability in large finite networks, in any equilibrium. We also give examples of nonegalitarian networks with equilibria in which learning fails.     

Ex Ante and Ex Post: What Does Rod Stewart Really Know Now?1

Do we really know whether or not we have “maximized” utility, or do we just know that we are “happy” or “sad”? We argue that we can never know objectively whether or not utility has been maximized; however, people acting on a free market are sufficiently close to the decision as to be able to hazard a better guess about their opportunity costs than policy makers.     

Multi-goal optimization in managerial science

A number of modern economists have accepted alternatives to the basic hypothesis of neo-classical economics that the overriding objective of any firm is to maximize the owner's (shareholder's) welfare. However, with one or two outstanding exceptions, these alternatives have been ignored by managerial scientists, whose economics related models continue to be formulated in terms of the neo-classical hypothesis. This paper treats the implications of those alternatives which deny that corporate management is trying to optimize any single goal—let alone shareholder welfare. More specifically, this paper discusses management science models involving the allocation of scarce resources to satisfy several goals. The resulting multi-goal “optimization” problem is identified as a vector “maximization” problem and is formulated in terms of the efficient point concept.     

一种基于TOPSIS的混合型多属性群决策方法

本文针对具有语言型和直觉模糊数两种评价信息的混合型多属性群决策问题,提出了一种基于TOPSIS的决策方法。首先,定义了新的函数,可将不同粒度的语言评价信息转换成直觉模糊数。其次,在直觉模糊数熵值的基础上,提出了一种新的专家权重确定模型。再次,利用IFWA算子在把个体决策矩阵集结为群体决策矩阵后,基于TOPSIS分别计算群体评价值到正理想解和负理想解的距离,从而得到方案集的排序。最后,在ERP选优问题中的应用,验证了方法的有效性。