Stochastic Judgments in the AHP: The Measurement of Rank Reversal Probabilities

This paper presents a methodology for analyzing Analytic Hierarchy Process (AHP) rankings if the pairwise preference judgments are uncertain (stochastic). If the relative preference statements are represented by judgment intervals, rather than single values, then the rankings resulting from a traditional (deterministic) AHP analysis based on single judgment values may be reversed, and therefore incorrect. In the presence of stochastic judgments, the traditional AHP rankings may be stable or unstable, depending on the nature of the uncertainty. We develop multivariate statistical techniques to obtain both point estimates and confidence intervals of the rank reversal probabilities, and show how simulation experiments can be used as an effective and accurate tool for analyzing the stability of the preference rankings under uncertainty. If the rank reversal probability is low, then the rankings are stable and the decision maker can be confident that the AHP ranking is correct. However, if the likelihood of rank reversal is high, then the decision maker should interpret the AHP rankings cautiously, as there is a subtantial probability that these rankings are incorrect. High rank reversal probabilities indicate a need for exploring alternative problem formulations and methods of analysis. The information about the extent to which the ranking of the alternatives is sensitive to the stochastic nature of the pairwise judgments should be valuable information into the decision-making process, much like variability and confidence intervals are crucial tools for statistical inference. We provide simulation experiments and numerical examples to evaluate our method. Our analysis of rank reversal due to stochastic judgments is not related to previous research on rank reversal that focuses on mathematical properties inherent to the AHP methodology, for instance, the occurrence of rank reversal if a new alternative is added or an existing one is deleted.     

PAHAP: A Pairwise Aggregated Hierarchical Analysis of Ratio-Scale Preferences

In this paper, we present a Pairwise Aggregated Hierarchical Analysis of Ratio-Scale Preferences (PAHAP), a new method for solving discrete alternative multicriteria decision problems. Following the Analytic Hierarchy Process (AHP), PAHAP uses pairwise preference judgments to assess the relative attractiveness of the alternatives. By first aggregating the pairwise judgment ratios of the alternatives across all criteria, and then synthesizing based on these aggregate measures, PAHAP determines overall ratio scale priorities and rankings of the alternatives which are not subject to rank reversal, provided that certain weak consistency requirements are satisfied. Hence, PAHAP can serve as a useful alternative to the original AHP if rank reversal is undesirable, for instance when the system is open and criterion scarcity does not affect the relative attractiveness of the alternatives. Moreover, the single matrix of pairwise aggregated ratings constructed in PAHAP provides useful insights into the decision maker's preference structure. PAHAP requires the same preference information as the original AHP (or, altematively, the same information as the Referenced AHP, if the criteria are compared based on average (total) value of the alternatives). As it is easier to implement and interpret than previously proposed variants of the conventional AHP which prevent rank reversal, PAHAP also appears attractive from a practitioner's viewpoint.     

Dependence Assessment in Human Reliability Analysis Using Evidence Theory and AHP

Dependence assessment among human errors in human reliability analysis (HRA) is an important issue. Many of the dependence assessment methods in HRA rely heavily on the expert's opinion, thus are subjective and may sometimes cause inconsistency. In this article, we propose a computational model based on the Dempster‐Shafer evidence theory (DSET) and the analytic hierarchy process (AHP) method to handle dependence in HRA. First, dependence influencing factors among human tasks are identified and the weights of the factors are determined by experts using the AHP method. Second, judgment on each factor is given by the analyst referring to anchors and linguistic labels. Third, the judgments are represented as basic belief assignments (BBAs) and are integrated into a fused BBA by weighted average combination in DSET. Finally, the CHEP is calculated based on the fused BBA. The proposed model can deal with ambiguity and the degree of confidence in the judgments, and is able to reduce the subjectivity and improve the consistency in the evaluation process.     

On the Selection of Distributions for Stochastic Variables

One of the main steps in an uncertainty analysis is the selection of appropriate probability distribution functions for all stochastic variables. In this paper, criteria for such selections are reviewed, the most important among them being any a priori knowledge about the nature of a stochastic variable, and the Central Limit Theorem of probability theory applied to sums and products of stochastic variables. In applications of these criteria, it is shown that many of the popular selections, such as the uniform distribution for a poorly known variable, require far more knowledge than is actually available. However, the knowledge available is usually sufficient to make use of other, more appropriate distributions. Next, functions of stochastic variables and the selection of probability distributions for their arguments as well as the use of different methods of error propagation through these functions are discussed. From these evaluations, priorities can be assigned to determine which of the stochastic variables in a function need the most care in selecting the type of distribution and its parameters. Finally, a method is proposed to assist in the assignment of an appropriate distribution which is commensurate with the total information on a particular stochastic variable, and is based on the scientific method. Two examples are given to elucidate the method for cases of little or almost no information.     

多专家判断的模糊偏好信息集结规划方法

本文给出了一种群决策中通过专家判断矩阵集结专家判断信息的方法。在考虑各专家具有不同强度的偏好效用和容许部分专家给出不完整信息的情况下,将专家判断信息集结转化为一类模糊规划问题,通过最大化群组满意度获得最终的群决策结果。最后,本文通过一个算例说明该方法的可行性及有效性。     

Stochastic orders and non-Gaussian risk factor models

The main results of this paper are monotonicity statements about the risk measures value-at-risk (VaR) and tail value-at-risk (TVaR) with respect to the parameters of single and multi risk factor models, which are standard models for the quantification of credit and insurance risk. In the context of single risk factor models, non-Gaussian distributed latent risk factors are allowed. It is shown that the TVaR increases with increasing claim amounts, probabilities of claims and correlations, whereas the VaR is in general not monotone in the correlation parameters. To compare the aggregated risks arising from single and multi risk factor models, the usual stochastic order and the increasing convex order are used in this paper, since these stochastic orders can be interpreted as being induced by the VaR-concept and the TVaR-concept, respectively. To derive monotonicity statements about these risk measures, properties of several further stochastic orders are used and their relation to the usual stochastic order and to the increasing convex order are applied.     

A Rejoinder to Forman on AHP,with Emphasis on the Requirements of Composite Ratio Scales*

In an earlier paper [11], the problems of rank reversals and invalid composite priorities in AHP were addressed by modifications to the AHP procedure. That solution was subsequently criticized [5]. In this paper, we rebut these criticisms, and we show how rank reversals in AHP can arise merely from the process of normalizing local priorities.     

群体两两比较判断集成的最短距离方法

本文将Yu和Cook等提出的一般距离的概念应用到群体决策问题中,基于AHP原理,给出了群体决策集成问题的定义,综述了现有的两两比较判断集成方法,提出了一种基于最短距离的集成方法——最短距离方法(Mini-mum Distance Method,MSM),并用数值例示进行了说明,最后讨论了群体决策以及AHP未来可能的研究课题。     

The analytic hierarchy process with interval preference statements

In the analytic hierarchy process (AHP), interval judgments instead of precise ratios are widely accepted and can be practically used to solve decision-making problems when uncertainty exists because of scant information available or insufficient understanding of the problem. This paper presents a simple and effective method for finding the extreme points in a range of interval ratios (such as loose articulation, minimum number of interval ratios, and general interval ratios) and ultimately for establishing the dominance relations among alternatives using the identified extreme points. This is followed by an enumeration or simulation approach to manage situations in which the best or a full ranking of alternatives remains unidentified.     

A qualitative perspective to deriving weights from pairwise comparison matrices

Deriving weights from pairwise comparison matrices (PCM) is a highly researched topic. The analytic hierarchy process (AHP) traditionally uses the eigenvector method for the purpose. Numerous other methods have also been suggested. A distinctive feature of all these methods is that they associate a quantitative meaning to the judgemental information given by the decision-maker. In contrast, the verbal scale used in AHP to capture judgements does not associate such a quantitative meaning. Though this issue of treating judgements qualitatively is recognized in the extant literature on multi-criteria decision making, unfortunately, there is no research effort so far in the AHP literature. Deriving motivation from the application of data envelopment analysis (DEA) for deriving weights, it is proposed in this paper that DEA models developed to deal with a mix of qualitative and quantitative factors can be used to derive weights from PCMs by treating judgements as qualitative factors. The qualitative DEA model is discussed and illustrated in this paper.     

LEVY-LIBOR市场模型的蒙特卡罗模拟参数校准与估计

基于远期LIBOR利率的随机波动与无限跳跃特征，针对标准化LIBOR市场模型（LMM）和随机波动率LIBOR市场模型（SV-LMM）应用局限，进一步引入Levy无限跳跃过程，建立多因子非标准化Levy 跳跃随机波动率LIBOR市场模型（SVLEVY-LMM）。在此基础上，基于非参数化相关矩阵假设，运用互换期权（Swaption）、利率上限（Cap）等主要市场校准工具和蒙特卡罗模拟技术，对模型局部波动率和瞬间相关系数等参数进行有效市场校准；应用自适应马尔科夫链蒙特卡罗模拟方法（A-MCMC）对Levy跳跃与随机波动参数进行有效理论估计。实证认为，对远期利率波动率校准，分段固定波动率结构较为符合市场实际情况；对远期利率相关系数矩阵校准，非参数化相关系数矩阵具有最小估计误差和最佳的市场适应性；SVLEVY-LMM能够最好拟合远期LIBOR利率。     

Combining Experts' Risk Judgments on Technology Performance of Phytoremediation: Self-Confidence Ratings, Averaging Procedures, and Formative Consensus Building

Expert panels and averaging procedures are common means for coping with the uncertainty of effects of technology application in complex environments. We investigate the connection between confidence and the validity of expert judgment. Moreover, a formative consensus building procedure (FCB) is introduced that generates probability statements on the performance of technologies, and we compare different algorithms for the statistical aggregation of individual judgments. The case study refers to an expert panel of 10 environmental scientists assessing the performance of a soil cleanup technology that uses the capability of certain plants to accumulate heavy metals from the soil in the plant body (phytoremediation). The panel members first provided individual statements on the effectiveness of a phytoremediation. Such statements can support policymakers, answering the questions concerning the expected performance of the new technology in contaminated areas. The present study reviews (1) the steps of the FCB, (2) the constraints of technology application (contaminants, soil structure, etc.), (3) the measurement of expert knowledge, (4) the statistical averaging and the discursive agreement procedures, and (5) the boundaries of application for the FCB method. The quantitative statement oriented part of FCB generates terms such as: "The probability that the concentration of soil contamination will be reduced by at least 50% is 0.8." The data suggest that taking the median of the individual expert estimates provides the most accurate aggregated estimate. The discursive agreement procedure of FCB appears suitable for deriving politically relevant singular statements rather than for obtaining comprehensive information about uncertainties as represented by probability distributions.     

Environmental Risk, Precaution, and Scientific Rationality in the Context of WTO/NAFTA Trade Rules

This article considers the role of scientific rationality in understanding statements of risk produced by a scientific community. An argument is advanced that, while scientific rationality does impose constraints on valid scientific justifications for restrictions on products and practices, it also provides flexibility in the judgments needed to both develop and apply characterizations of risk. The implications of this flexibility for the understanding of risk estimates in WTO and NAFTA deliberations are explored, with the goal of finding an intermediate ground between the view that science unambiguously justifies or rejects a policy, and the view that science is yet another cultural tool that can be manipulated in support of any decision. The result is a proposal for a dialogical view of scientific rationality in which risk estimates are depicted as confidence distributions that follow from a structured dialogue of scientific panels focused on judgments of evidence, evidential reasoning, and epistemic analysis.     

Decision Support by Interval SMART/SWING—Incorporating Imprecision in the SMART and SWING Methods

Interval judgments are a way of handling preferential and informational imprecision in multicriteria decision analysis (MCDA). In this article, we study the use of intervals in the simple multiattribute rating technique (SMART) and SWING weighting methods. We generalize the methods by allowing the reference attribute to be any attribute, not just the most or the least important one, and by allowing the decision maker to reply with intervals to the weight ratio questions to account for his/her judgmental imprecision. We also study the practical and procedural implications of using imprecision intervals in these methods. These include, for example, how to select the reference attribute to identify as many dominated alternatives as possible. Based on the results of a simulation study, we suggest guidelines for how to carry out the weighting process in practice. Computer support can be used to make the process visual and interactive. We describe the WINPRE software for interval SMART/SWING, preference assessment by imprecise ratio statements (PAIRS), and preference programming. The use of interval SMART/SWING is illustrated by a job selection example.     

STOCHASTIC COST-VOLUME-PROFIT ANALYSIS WITH A LINEAR DEMAND FUNCTION

In this paper we incorporate a linear demand function to model the price-volume causal relationship into stochastic cost-volume-profit (CVP) analysis. We assume that the objective function is to maximize expected profit; other objective functions are also discussed and compared. A linear stochastic model follows from which probabilistic statements can be easily obtained if the random variables are assumed to be multivariate normal. The basic framework is shown to be a special case of project value maximization where project value is the cash flow of the project discounted for time and risk according to the capital asset pricing model. Moreover, an intertemporal extension that considers inventory is developed. In summary, a new approach to stochastic CVP analysis that incorporates the management decision process in an uncertain environment is developed.     

一种基于方差最大化的组合赋权评价方法及其应用

粗糙集权重确定方法利用属性重要度来确定属性的客观权重,这种方法克服了权重确定过分依赖专家经验知识的不足,但也忽略了各属性指标本身的重要性问题。本文将粗糙集权重确定方法与专家主观赋权的层次分析法相结合,基于方差最大化的原理提出了一种主客观组合赋权方法。粗糙集结合主观层次分析法的组合权重很好地将两者的优点有效结合,同时方差最大化原理也对传统组合权重确定方法进行了改进,使得权重的确定更加合理,更能有助于决策者做出决策。最后,用一个算例应用证明了该种组合赋权决策方法的可行性。     

目标导向层次分析方法

对含有抽象属性的多属性层次结构而言,层次分析法即AHP（包括DIS-AHP、ABS-AHP、IDE-AHP和SUP-AHP四种具体方法）会因比率比较基准缺失、权重内涵模糊不清或方案评价不保序而缺乏科学理性。为发展AHP,基于摆幅置权（SW）判断模式和多属性决策属性价值公度方法,首先给出了能为层次结构抽象属性上的SW判断提供支持的规约性多属性决策属性价值公度方法,然后由此并结合多属性价值理论给出了能够克服现有层次分析法内在缺陷的目标导向层次分析方法即ToAHP。相对于AHP,ToAHP在判断模式与权重内涵、方法建构的理论基础和相关假设检验、方案评价保序与其内在数理依据上具有明显的相对科学合理性。应用分析表明：在输入信息可比的条件下,ToAHP明显优于AHP的四种分析方法之中最具可信性的SUP-AHP方法。     

基于最小偏差组合权重的突发事件应急能力评价模型

在突发事件应急能力评价问题中存在着不同评价方法的冲突性,即群决策评价结果的方法依赖性问题。本文以高速公路突发事件应急能力评价为研究对象,提出了基于最小偏差组合权重的评价模型。首先,系统地分析了高速公路突发事件应急能力的评价问题,建立了基于过程管理的高速公路突发事件应急能力评价的指标体系。根据语言评价指标分别运用二元语义层次分析法、G1主观赋权法和基于熵值法的二元语义赋权法等三种方法确定各评价指标的权重,然后综合各种评价方法构建了基于最小偏差的组合权重线性规划模型,确定准则层的最优复合权重,得出高速公路应急能力的评价值。最后,以上海"9·14"重大道路交通事故作为应急能力评价的分析案例,比较了不同评价模型的结果,并对评价指标进行敏感性分析。研究结果表明,基于最小偏差组合权重的评价模型能够在多个评价模型中达到最大的一致性,从而有效地减少了群决策中不同主客观评价方法的"极化"效应。     

AHP DESIGN ISSUES FOR LARGE-SCALE SYSTEMS

The analytic hierarchy process (AHP) is a decision analysis technique that uses judgments from a group of relevant decision makers and hierarchical decomposition to derive a set of ratio-scaled utility measures for decision alternatives. This paper addresses a number of design issues involved in the implementation of AHP for large-scale systems. Specifically, it describes the use of incomplete experimental designs for simplifying data-collection tasks. The effects of reducing the size of the hierarchy through attribute deletion and the effects of including identical attributes on any given level also are evaluated.     

Modeling Extreme Risks in Ecology

Extreme risks in ecology are typified by circumstances in which data are sporadic or unavailable, understanding is poor, and decisions are urgently needed. Expert judgments are pervasive and disagreements among experts are commonplace. We outline approaches to evaluating extreme risks in ecology that rely on stochastic simulation, with a particular focus on methods to evaluate the likelihood of extinction and quasi‐extinction of threatened species, and the likelihood of establishment and spread of invasive pests. We evaluate the importance of assumptions in these assessments and the potential of some new approaches to account for these uncertainties, including hierarchical estimation procedures and generalized extreme value distributions. We conclude by examining the treatment of consequences in extreme risk analysis in ecology and how expert judgment may better be harnessed to evaluate extreme risks.