Showing papers on "Pairwise comparison published in 1988"
TL;DR: An approach for performing multiple alignments of large numbers of amino acid or nucleotide sequences is described, based on first deriving a phylogenetic tree from a matrix of all pairwise sequence similarity scores obtained using a fast pairwise alignment algorithm.
3,518 citations
TL;DR: The problem of weight derivation is shown to be equivalent to that of finding a totally transitive matrix which is a minimum distance from the given matrix, and the uniqueness of the measure is proven.
107 citations
01 Jan 1988
TL;DR: In this article, the choice between 2 and 3SLS for full-system estimation was made based on statistical efficiency and computational cost. But the choice was not made only on the statistical efficiency but also on the strength of the interrelations among the error terms.
Abstract: Two elements enter the choice between 2 and 3SLS for full-system estimation: statistical efficiency and computational cost. 2SLS always has the computational edge, but 3SLS can be more efficient, a relative advantage that increases with the strength of the interrelations among the error terms. A measure of these interrelations is thus helpful in making the choice, and, when there are only two equations, this has suggested using a high pairwise error correlation as an indicator of when to use 3SLS. In larger systems of equations, however, these pairwise correlations can remain small even though more general interrelations give 3SLS the relative advantage. More general indicators are therefore needed, and this paper suggests three such and demonstrates their efficacy.
86 citations
TL;DR: The 'regions' method for multisequence alignment used in the previously reported program MALIGN has been generalized to include recursive refinement so that unaligned portions between two regions at the current level of resolution can be handled with increased resolution.
Abstract: The 'regions' method for multisequence alignment used in the previously reported program MALIGN has been generalized to include recursive refinement so that unaligned portions between two regions at the current level of resolution can be handled with increased resolution. Additionally, there is incorporated a limiting of the number of regions to be used at any level of resolution from which to abstract an alignment. This provides a significant increase in speed over the unlimited version. The program GENALIGN uses this improved regions method to execute fast pairwise alignments in the framework of Taylor's multisequence alignment procedure using clustered pairwise alignments. Pairwise alignments by dynamic programming are also provided in the program.
73 citations
01 Dec 1988
TL;DR: In this article, a multi-criteria problem of how to choose the best item from a finite set of alternatives is considered, when none of the alternative tools for attaining it seems to be perfect.
Abstract: We are concerned with the multi-criteria problem of how to choose the best item from a finite set of alternatives. We face such a decision problem when we want to attain a goal, and when none of the alternative tools for attaining it seems to be perfect. In general, we consider the alternatives from various viewpoints, and we estimate how well they enable us to attain the goal. Briefly speaking, we estimate the relative importance of the criteria, and we express it in numerical weights. Similarly, we estimate the relative importance of the alternatives under each of the criteria separately. Lastly, we aggregate the weights to obtain a final score for each alternative. With this information, we are in a position to rank and rate the alternatives, and to select the best compromise.
57 citations
TL;DR: An application of the analytic hierarchy approach (AHP) to predict the ranking of the 16 soccer teams of the Israeli National League with six criteria (attributes) used for evaluating each team.
Abstract: This paper presents an application of the analytic hierarchy approach (AHP) to predict the ranking of the 16 soccer teams of the Israeli National League. Six criteria (attributes) were used for evaluating each team: the team's facility, the team's trainer, the players' level, the team's fans, the previous season's performance and the current performance. For each criterion a matrix of pairwise comparisons between teams was evaluated by a sports expert. The normalized eigenvector of each matrix scales the teams with regard to that criterion. The overall scaling is constructed by weighting the scales of all the criteria. The weight of the criteria are extracted from a judgemental matrix of pairwise comparisons between every two criteria. The normalized eigenvector of this matrix provides the criteria weights. Some comparisons to simpler ranking methods were made in order to validate the model.
37 citations
TL;DR: A method of computing upper and lower bounds on the pairwise Bayes risk for composite classes is developed and numerical examples of the application of the bounding techniques to a problem involving the classification of aircraft are discussed.
Abstract: Upper and lower bounds on the Bayes risk for multiple, composite-hypothesis classification are obtained. Bounds on the Bayes risk for M simple classes are derived in terms of the risk functions for (M-1) classes, and so on, until the desired result depends only on the pairwise (M=2) Bayes risks. A method of computing upper and lower bounds on the pairwise Bayes risk for composite classes is developed. Algorithms for computing the upper and lower bounds for the general M-class case and for composite-hypothesis classes are presented. Numerical examples of the application of the bounding techniques to a problem involving the classification of aircraft are discussed. Results for the bounds and other performance measures are compared for the most interesting cases. >
35 citations
TL;DR: In this paper, an approach for the problem of choosing among discrete alternatives assuming that criteria are ordinal is presented, which requires pairwise comparisons of alternatives by the decision maker and presumably inferior alternatives are eliminated.
Abstract: The existence of ordinal criteria is a factor that complicates multiple criteria problems. In this article we develop an approach for the problem of choosing among discrete alternatives assuming that criteria are ordinal. The approach requires pairwise comparisons of alternatives by the decision maker. Based on these comparisons, presumably inferior alternatives are eliminated. Experience on randomly generated problems indicates that the approach usually chooses one of the most preferred alternatives and requires a small number of pairwise comparisons.
29 citations
TL;DR: The essential ordering significantly reduces the number of possible rankings of the rules, and thus, simplifies the development of the ranking algorithm and has important applications when the available information on the experts' decisional skills is incomplete.
Abstract: For small panels of experts (e.g., boards of managers, courts, specialized committees), n ≦ 5, this paper provides an algorithm for ranking the seven efficient and commonly used weighted majority rules by their respective performance. These rules are terned efficient since they constitute the set of potentially optimal decision rules in uncertain, symmetric, pairwise choice situations. The main contribution of this study is the discovery of an essential ordering of six of these rules which entails that the set of possible ranking of the seven rules is almost single peaked. The essential ordering significantly reduces the number of possible rankings of the rules, and thus, simplifies the development of the ranking algorithm. The essential ordering has important applications when the available information on the experts' decisional skills is incomplete.
19 citations
TL;DR: In this article, a method is described for pairwise comparison of real and real landscapes aimed at the detection of the most important preference criteria, such as depth of field of vision.
Abstract: A method is described (or the pairwise comparison of real landscapes aimed at the detection of the most important preference criteria. We conclude that “depth of field of vision” is a dominant characteristic influencing many preference decisions. The influence of this factor is not detected when photographs instead of real landscapes are used.
15 citations
Journal Article•
TL;DR: A tool such as the AHP enables the manager and hospital to gain control of resources by saving time in reaching a decision, double checking other decisions for validity, using the model to audit department head decisions, and standardizing the decision-making process.
Abstract: A useful tool to assist management with complex multiple-criteria decision making is the analytic hierarchy process (AHP) microcomputer program. The AHP requires the user to judge the relative importance of each criterion, then specify a preference for each alternative relative to each criterion. The result is a prioritized overall ranking of the decision alternatives. Providence Ventures, Inc., used the AHP to assist a recent hospital client in selecting a magnetic resonance imaging vendor. A committee was appointed to narrow the decision alternatives down to three vendors, using the following criteria: price, technology, sitting, service, service contract, cryogen contract, and patient comfort. A key factor in the AHP is establishing priorities and preferences through the pairwise comparison procedure. The program asks the user, for example, if price and technology are equally important. If the response is no, the user tells the program which is more important and by how much, assigning a weight to each criterion. Similarly the user enters pairwise preferences for the vendors in regard to each criterion. The program then computes the overall decision. The entire process takes 10 to 15 minutes. A tool such as the AHP enables the manager and hospital to gain control of resources by saving time in reaching a decision, double checking other decisions for validity, using the model to audit department head decisions, and standardizing the decision-making process.
TL;DR: In this article, the authors employ the compatibility matrix approach and derive statistical relationships for the estimation of the mean and standard deviation number of feasible alternsitives plans for a project network consisting of activities that have many alternatives and pairwise compatibility relationships.
Abstract: A project network consists of activities that have many alternatives and pairwise compatibility relationships. This paper employs the compatibility matrix approach and derives statistical relationships for the estimation of the mean and standard deviation number of feasible alternsitives plans.
TL;DR: In this paper, a relational system of preferences (Hyper-Order) based on a generalization of the property of transitivity is proposed avoiding some shortcomings of previous contributions to model the prefenreces of decision makers.
22 Aug 1988
TL;DR: The object and relational c-means algorithms, and the theory asserting their duality in case the relational data corresponds to an inner-product induced measure of distance between each pair of corresponding object data are reviewed.
Abstract: In this note we review the object and relational c-means algorithms, and the theory asserting their duality in case the relational data corresponds to an inner-product induced measure of distance between each pair of corresponding object data. Past numerical results are given here along with new extensions in order to study the effect of the choice of pairwise distance measure on the relational partition obtained.
TL;DR: In this article, it was shown that the sufficient sublattices are exactly the fixed spaces of the subsemigroups of the semigroup of all measure-wise experiment-preserving positive operators on the M-space of the experiment.
Abstract: For a statistical experiment LeCam [3] introduced the concept of a sufficient sublattice (in the M-space of the experiment) thus replacing the usual measure theoretic notion of sufficiency by a vector lattice framework. In this note it is pointed out that the sufficient sublattices are exactly the fixed spaces of the subsemigroups of the semigroup of all measurewise experiment-preserving positive operators on the M-space of the experiment. So reduction of an experiment by sufficiency and reduction by invariance coincide. We derive the same result for pairwise sufficient subfields and sufficient subfields under suitable conditions on the experiment. Some examples which concern the semigroup of operators arising from measurewise experiment-preserving point transformations are given. This is related to Basu's [1] work.
TL;DR: The method provides a predictive evaluation of the probability of the commercial success of technological breakthroughs and is a quantification of the qualitative method originally developed by White and Graham.
Abstract: The purpose of the paper is to suggest a quantitative method for analyzing the innovation risk from both technological and an economic point of view as a contribution to the strategic evaluation and planning process. Specifically the method provides a predictive evaluation of the probability of the commercial success of technological breakthroughs.
The method is a quantification of the qualitative method originally developed by White and Graham. It consists of a stepwise process in which the benefits of a technology are classified under four major headings: inventive merit, embodiment merit, market merit, and operational merit. Within each heading, the target technology is evaluated by pairwise comparison with alternative technologies, using a Saaty-type procedure. The decision-maker can conduct a sensitivity analysis and the evaluation can be made collaborative by using a group of judges.
The methodology which is computerized is described in some detail. Its use is illustrated by applying it to an hypothetical project in the field of information retrieval in which CD-ROM is compared with three alternative technologies.
TL;DR: A methodology for the assessment of a decision-maker's utility function, based on interactions requiring relatively easy responses of the implicit trade-off type, i.e. similar to responses required in STEM or goal programming methods is introduced.
Abstract: This paper introduces a methodology for the assessment of a decision-maker's utility function, based on interactions requiring relatively easy responses of the implicit trade-off type, i.e. similar to responses required in STEM or goal programming methods. The estimation of the value-function model to represent preferences is useful in ranking or pruning elements of the decision space. Inputs required from the decision-maker are, however, less demanding than the pairwise comparisons (or similar preference statements) typically required by value-function models. The methodology thus appears to be appropriate for relatively large numbers of criteria. An algorithm for implementing the proposed methodology for finite action spaces is developed and applied to examples involving up to 15 criteria.
01 Jan 1988
TL;DR: In this paper, a sample size selection procedure for paired comparisons of means is presented which controls the half width of the confidence intervals while allowing for unequal variances of treatment means, and a sample selection procedure is presented for paired comparison of means.
Abstract: A sample size selection procedure for paired comparisons of means is presented which controls the half width of the confidence intervals while allowing for unequal variances of treatment means.
01 Jun 1988
TL;DR: A evaluation method using fuzzy checklist where check items are rated as fuzzy numbers is illustrated, where pairwise comparison data is used to determine the weights of check items, since it has comparative advantage for human's fuzzy judgment.
Abstract: Checklist method is rapid and comprehensive to evaluate in practice. Check items are commonly rated by subjective utility function; i.e., evaluator's significant judgment. Since human judgment includes fuzziness (vagueness) inherently in spite of its significance, fuzzy set theory is useful in this case. The paper illustrates a evaluation method using fuzzy checklist where check items are rated as fuzzy numbers. Pairwise comparison data is used to determine the weights of check items, since it has comparative advantage for human's fuzzy judgment. Sample of BASIC program is provided for microcomputer. When uncertainty is due to subjectivity or imprecision of data, this method can be applied to practical problems widely.