Rect@ (Jan 2007)
An analysis of the DEA-based methods for aggregating ordinal rankings
Abstract
Scoring rules are a well-known class of ranked voting systems where fixed scores are assigned to the different ranks. To avoid the use of a fixed scoring vector, Cook and Kress [Management Science 36, pp. 1302-1310, 1990] introduced a DEA model so that each candidate may be assessed with the most favorable scoring vector for him/her. However, this procedure often causes that several candidates are efficient, i.e., they achieve the maximum score. For this reason, several methods to discriminate among efficient candidates have been proposed. The aim of this work is to show some drawbacks of these methods.
