Showing papers on "Pairwise comparison published in 1984"
254 citations
TL;DR: In this paper, an interactive method employing pairwise comparisons of attainable solutions is developed for solving the discrete, deterministic multiple criteria problem assuming a single decision maker who has an implicit quasi-concave increasing utility (or value) function.
Abstract: An interactive method employing pairwise comparisons of attainable solutions is developed for solving the discrete, deterministic multiple criteria problem assuming a single decision maker who has an implicit quasi-concave increasing utility (or value) function. The method chooses an arbitrary set of positive multipliers to generate a proxy composite linear objective function which is then maximized over the set of solutions. The maximizing solution is compared with several solutions using pairwise judgments asked of the decision maker. Responses are used to eliminate alternatives using convex cones based on expressed preferences, and then a new set of weights is found that satisfies the indicated preferences. The requisite theory and proofs as well as a detailed numerical example are included. In addition, the results of some computational experiments to test the effectiveness of the method are described.
221 citations
01 Jan 1984
TL;DR: An approach is presented for solving a discrete-multiple-criteria problem that asks pairwise comparisons of a decision-maker and generally yields the most preferred alternative after several comparisons, usually fewer than 20.
Abstract: An approach is presented for solving a discrete-multiple-criteria problem The approach asks pairwise comparisons of a decision-maker Under mild assumptions, the method obtains the most preferred alternative The required number of pairwise comparisons is generally modest The authors' experience with the method indicates that for reasonable underlying utility functions, a heuristic stopping rule generally yields the most preferred alternative after several comparisons, usually fewer than 20
86 citations
01 Jan 1984
TL;DR: The Analytic Hierarchy Process is a problem solving framework that organizes the basic rationality by breaking down a problem into its smaller constituent parts and then calls for only simple pairwise comparison judgments, to develop priorities in each hierarchy.
Abstract: The Analytic Hierarchy Process (AHP) is a problem solving framework. It is a systematic procedure for representing the elements of any problem. It organizes the basic rationality by breaking down a problem into its smaller constituent parts and then calls for only simple pairwise comparison judgments, to develop priorities in each hierarchy.
84 citations
TL;DR: In this paper, the pairwise divergence measure is used for the best feature selection and to determine the statistical separability among the pair of classes in remote sensing literature, and some of the confusion pertaining to this measure in Remote Sensing literature have been clarified.
Abstract: A pairwise divergence measure is often used for the best feature selection and to determine the statistical separability among the pair of classes. In this communication some of the confusion pertaining to this measure in remote sensing literature have been clarified.
31 citations
30 citations
TL;DR: A network flow model is used for budget allocation in a multi-campus institution over several years that maximizes the additive utility function of the institution, expressed as a weighted summation over the preferences of the three hierarchies.
Abstract: A network flow model is used for budget allocation in a multi-campus institution over several years. The network had a hierarchical structure with three hierarchies. The network's lower bounds represent the minimal requirements for each component. The upper bounds represent the predicted future requirement. They are predicted via a cost simulation model where several volume indices, policy variables and some environmental factors are used. Thus the overall planning process combines simulation with optimization. The model maximizes the additive utility function of the institution, expressed as a weighted summation over the preferences of the three hierarchies. The preferences are evaluated by using a multi-goal approach, utilizing pairwise comparisons and the eigenvalue prioritization technique developed by T. Saaty.
29 citations
TL;DR: A continuous metric is proposed which ameliorates information loss and unreliability in high density regions of the data and is suitable for correlational analyses.
Abstract: When considering psychological constructs in a pairwise fashion, a 2 x 2 category system, based on median splits, is often adopted for analytic convenience. If theoretical focus is on an individual's integration of the two constructs, then categorical procedures are subject to information loss and unreliability in high density regions of the data. A continuous metric is proposed which ameliorates these problems and is suitable for correlational analyses. The construct of psychological androgyny is used for illustrative purposes.
23 citations
15 citations
TL;DR: A seven cell partition of N is constructed with the property that no infinite set has all of its pairwise sums and products in any one cell.
13 citations
TL;DR: Following the approach taken by Fishburn (1980), the algebraic axiomatization of an additive difference model for pairwise choices between multi-attribute stimuli is discussed in this article, where it is shown that the multiplicative difference model can be expressed as a pairwise choice.
Abstract: Following the approach taken by Fishburn (1980), the algebraic axiomatization of an additive difference model for pairwise choices between multi-attribute stimuli is discussed.
TL;DR: In this paper, the performance of paired versus joint ranking procedures for pairwise multiple comparisons is investigated using approxiirete Bahadur efficiency, when the populations to be compared are widely separated, or-when the data arise from a shift model with an underlying unimodal density.
Abstract: The performance of paired versus joint ranking procedures for pairwise multiple comparisons is investigated using approxiirete Bahadur efficiency, When the populations to be compared are widely separated, or-when the. data arise from a shift model with an underlying unimodal density, the paired ranking procedure is found to be better for comparing two adjacent populations while the joint ranking procedure is more efficient for comparing the two most distant populations
TL;DR: In this article, it is demonstrated that much stronger evaluations of preference are possible by applying formal statistical inferential procedures to a simple parametric model, relating indifference to closeness on a scale defined by a linear function of attribute values.
Abstract: Rivett [5] has proposed that an approximate preference ordering may be deduced from statements of pairwise indifferences between decision alternatives by using multi-dimensional scaling. In this paper it is demonstrated that much stronger evaluations of preference are possible by applying formal statistical inferential procedures to a simple parametric model, relating indifference to closeness on a scale defined by a linear function of attribute values. This can be used to screen out a considerable proportion of less desirable decision alternatives. The method is illustrated by application to Rivett's problem of the hypothetical Town of Brove, for which a satisfactory matching with Rivett's utilities is obtained. It is also shown that the method can provide useful preference orderings on the basis of less than 20% of all possible pairwise comparisons between alternatives.
TL;DR: It is argued that an approach to policy modelling in public planning must deal with the existence of conflicts between actors holding constraint sets, rather than players with strategies able to affect each other's payoffs.
Abstract: This paper argues that an approach to policy modelling in public planning must deal with the existence of conflicts between actors holding constraint sets, rather than players with strategies able to affect each other's payoffs. This approach builds on the policy level language proposed by Shiv K. Gupta and Laurence D. Richards. Operational definitions of modelling variables, conflict situations and potential pairwise coalitions are given. The approach is simple enough to allow manual calculation in small-scale problems and has a matrix notation which enables the use of computer programs for large-scale problems. A conceptual example which illustrates the features of the proposed modelling approach is presented and discussed.
01 May 1984
TL;DR: An algorithm for constructing the binary matrix model when needed is presented and can be used for deleting elements from the model and for making changes in the pairwise relations specified by the group during and/or after the ISM process.
Abstract: In the interpretative structural modelling (ISM) process a group consensus process is involved for developing subjective pairwise relations among the elements of a complex system. A binary matrix model is used to develop a complete relational pattern using the pairwise relations specified by the group. A computer is used for storing and processing the supplied information using simple logical operations. It is proposed that only the pairwise relations supplied by the group be stored. An algorithm for constructing the binary matrix model when needed is presented. The algorithm can also be used for deleting elements from the model and for making changes in the pairwise relations specified by the group during and/or after the ISM process. An example is given to illustrate the use of the algorithm.
TL;DR: A subjective pairwise comparison method is applied in transforming subjective information concerning the overall uncertainty of the stochastic system to fuzzy support, and a comparison of two fuzzy entropy functions is made.
Abstract: The overall uncertainty of an aging stochastic system is analyzed through the consideration of both objective uncertainty and subjective imprecision. The updated probability distribution of a normal variate is determined through the constructions of global and local entropy equations. A subjective pairwise comparison method is applied in transforming subjective information concerning the overall uncertainty of the stochastic system to fuzzy support. A comparison of two fuzzy entropy functions is made. Since the fuzzy entropy function is not unique, calibration on the actual probability distribution is needed in order to justify the use of the proposed expressions. However, in many practical situations it is possible to make sensible pairwise comparisons without being able to make sensible parameter estimates. In such circumstances the proposed scheme will be of value.
TL;DR: This article showed that the presence of these additional sentences significantly lowered performance and effects of presentation order were also observed, and order effects assumed to be due to memory load were differentially influenced by the increased number of presented sentences.
Abstract: Thirty-nine students constructed linear orderings (e.g., ABCD) from pairwise information (e.g., AB, BC, CD) presented in different orders. Construction took place when only pairwise information was presented, when one additional and irrelevant-to-the-ordering sentence was presented, and when two such additional sentences were presented. The presence of these additional sentences significantly lowered performance, and effects of presentation order were also observed. As predicted, order effects assumed to be due to memory load were differentially influenced by the increased number of presented sentences. Theoretical implications are discussed.
TL;DR: A nonparametric inference algorithm developed by Davis and Geman (1983) and applied to a medical prediction employs an estimation procedure for acquiring pairwise statistics among variables of a binary data set and employs a decision rule which asymptotically gives the minimum expected error.
Abstract: A nonparametric inference algorithm developed by Davis and Geman (1983) is extended problem. The algorithm and applied to a medical prediction employs an estimation procedure for acquiring pairwise statistics among variables of a binary data set, allows for the data-driven creation of interaction terms among the variables, and employs a decision rule which asymptotically gives the minimum expected error. The inference procedure was designed for large data sets but has been extended via the method of cross-validation to encompass smaller data sets.
TL;DR: In this article, a comparative study of ordering and selection procedures based on binary-type questions vs. standard methods based on pairwise comparisons was conducted, and the robustness of the procedures against minor errors in the compared values was formulated in terms of the probability of a correct selection.