A method for discriminating efficient candidates with ranked voting data

Ranked voting data arise when voters select and rank more than one candidate with order of preference. Cook and Kress introduced data envelopment analysis (DEA) to analyze ranked voting data. By using DEA, each candidate may use the most favorable weights for him/her to estimate his/her own preference score. However DEA often suggests that more than one unit are equally efficient. So, a method to discriminate these efficient candidates is needed. Some methods of such purpose are proposed. However, these methods have a weak point that the order of efficient candidates may be changed by existence of an inefficient candidate. In this paper, we propose a new method. Our method does not use information about inefficient candidates to discriminate efficient candidates. It is based on a very simple idea, and is realizable visually. So, we hope that it is acceptable to election officials.