Showing papers on "Pairwise comparison published in 1977"

Multiple comparisons in model i one-way anova with unequal variances

Abstract: A fixed effects one-way layout model of analysis of variance is considered where the variances are taken to be possibly unequal. Conservative single-stage procedures based on Banerjee’s method for the solution of the Behrens-Fisher problem are proposed for the following multiple comparisons problems: 1) all pairwise comparisons with a control population mean, and 2) all pairwise comparisons and all linear contrasts among the means. Since these procedures are likely to be very conservative in practice, approximate procedures based on Welch’s method for the solution of the Behrens-Fisher problem are suggested as alternatives. Monte Carlo studies indicate that the latter are much less conservative and hence may be better in practice. Both these sets of procedures need only the tables of the Student’s t-distribution for their application and are very simple to use. Exact two-stage procedures are proposed for the following multiple comparisons problems: 1) all pairwise comparisons and all linear contrasts amon...

Estimation of Interclass Correlation from Familial Data

Abstract: In the analysis of familial data in order to quantify the degree of parent–child resemblance several different estimators of interclass correlation, the pairwise, sib‐mean and random‐sib methods, have been used. We compare these methods and propose a new estimator, the ensemble estimator. For the case where there are a fixed number of siblings per family, the pairwise estimator is shown to be equivalent to the maximum likelihood estimator. When there are a variable number of siblings per family, the pairwise and ensemble estimators are shown by Monte Carlo simulation to be preferable due to their smaller mean square errors. When the sib‐sib correlation is low, the pairwise estimator is more effective whereas at high values the ensemble estimator is more effective.

The forward and backward processes of conflict analysis

Abstract: In this study, the forward process of planning is applied to conflict resolution, by structuring a conflict according to the levels of a conceptual hierarchy. The parties to the conflict form the first level, their objectives are at the second level, and possible solutions are at the third and final level. The elements at each level are weighted according to their relative importance by using the principal eigenvectors of a series of pairwise comparison matrices, and a weighting of the possible solutions is obtained. This forward process answers the question: given the present actors and their objectives, capabilities and policies, which outcome is the most likely to emerge? This technique is applied to a societal system, analyzing conflict in Northern Ireland. It is shown that the outcome which would in greatest measure satisfy the needs of all parties is one which gives legislative independence to Northern Ireland. This method of conflict resolution does not require long or involved calculations, and a means of further shortening the calculations is given. Unimportant branches of the hierarchy may be truncated. The use of hierarchies and the eigenvector method provides an efficient method for the evaluation of possible solutions of a conflict and provides valuable insights into the objectives of the parties and the way in which possible political structures might satisfy these objectives. This is a powerful technique to be added to the methods for conflict resolution.

A multicriteria analysis for water resource and land use development

Abstract: A new variant of the concordance analysis is developed and discussed in this paper. The concordance procedure in general is a multicriteria evaluation method for alternative projects. It is based on a pairwise comparison of (weighted) project outcomes, and it can be used both as an elimination method for less desirable projects and as a selection method of good projects. The new variant introduced in this paper is based on the idea of satisficing (or norm) project outcomes, which may serve as a frame of reference for the evaluation techniques. Such satisficing outcomes are also important in attacking the dimensional problems of a multicriteria analysis. The new concordance variant is illustrated by means of an empirical application to the selection of the most desirable plan out of a series of alternatives for the development of the Markerwaard area in the Netherlands. It is concluded that the concordance analysis is a useful tool in taking account of intangibles in water resource and land use design.

Pairwise comparisons involving unequal sample sizes associated with correlations, proportions or variances

Abstract: Attention is drawn to a procedure advocated by Spjotvoll & Stoline (1973) for making pairwise contrasts among k independent normal moans arising from samples with unequal sample sizes. The generality of the procedure is pointed out using transformations given by Levy (1975) for making comparisons among correlations, proportions or variances. An example is also provided.