A qualitative discriminant process for scoring and ranking in group support systems

Abstract

Group support systems (GSS) are increasingly being used within organizations to support group work. One area of support that is often desired is the scoring and ranking of alternatives on qualitative/subjective domains. In this article, we present a new, conceptual approach, the qualitative discriminant process, for scoring and ranking in GSS. This approach is based on well-established decision analysis techniques. It significantly advances the state of the art of GSS by addressing four common limitations: (1) the inability to deal with vagueness of human decision makers in articulating preferences; (2) difficulties in mapping qualitative evaluation to numeric estimates; (3) problems in aggregating individual preferences into meaningful group preference; and (4) the lack of simple, user-friendly techniques for dealing with a large number of decision alternatives. Our approach is easy to implement in stand-alone personal computers and GSS platforms. We illustrate this with a real-world problem on a prototype implementation. A qualitative discriminant process 391 Point Estimates Interval Estimates Interval Scales Category 1 Ratio Scales Category 2 Category 4 Category 3

Constructing confidence belief functions from one expert

“…In the past, many approaches are proposed to construct belief functions from the expert's opinions, such as (Bryson and Mobolurin, 1999;Bryson et al, 1994Bryson et al, , 1995Parsons, 1994;Shafer, 1976;Smets, 1990;Wong and Lingras, 1994;Wong et al, 1991;Yaghlane et al, 2006). However, the proposed method is not an alternative of these methods, which only constitute Step 2 in the procedure for generating the confidence BBA.…”

“…Parsons developed a qualitative binary theory of evidence, in which linguistic quantifiers were used to aid the transformation from the qualitative representation of belief to the numeric representation of belief, and the mass assignments represented by numeric intervals were dealt with (Parsons, 1994). A multi-process approach utilizing qualitative discrimination (Bryson, Ngwenyama, & Mobolurin, 1994) and pair-wise comparison (Bryson, Mobolurin, & Ngwenyama, 1995) came into being (Bryson & Mobolurin, 1999) because of the insufficient study of former methods at conceptual and experimental levels. Recently, a new method for eliciting qualitative belief functions in terms of preference relations transformed into the constraints of an optimization problem was proposed by Yaghlane, Denoeux, and Mellouli (2006).…”

Is your back-up IT infrastructure in a safe location?

“…5 Tree diagram for the categorization of alternatives subjective in nature, and involves the use of mathematical modeling for the gradual elimination of undesirable alternatives. This process was illustrated in a hypothetical and yet realistic case study where total cost functions (Canbolat et al 2007) and a slightly modified version of the qualitative discrimination process (Bryson et al 1994) were used as the mathematical techniques for generating the solution.…”

“…Expecting the decision maker to consistently indicate the importance of a decision criterion over another in numeric terms is unrealistic especially when there are a large number of criteria to be considered which would make the number of pair-wise comparisons very high. On the other hand, the qualitative discriminant process (QDP) developed by Bryson et al (1994) does not pose such demands on the decision makers, because it requires decision maker input in the form of a simple ranked list. The QDP, as described below, was designed for ranking alternatives on multiple criteria by a group of decision makers.…”

“…QDP was developed (Bryson et al 1994;Bryson 1997) for the facilitation of multi-criteria decision making in groups. The basic premise of the approach is that many decision making scenarios (such as location decisions) go beyond objective scoring, and involve subjective judgments of various alternatives.…”