A data envelopment model for aggregating preference rankings

This paper presents a general model for aggregating votes from a preferential ballot. The thrust of the model is to accord candidates a fair assessment in terms of their overall standing vis-a-vis first place, second place, place votes. The form of the model is a combined index where is the number of the place votes received by the candidate. The weights are assumed to form a monotonically decreasing sequence with. These constraints correspond to the assurance region (AR) side constraints in the DEA framework. The properties of the model are examined in terms of this discrimination intensity function d, and in the special case that, the present model is shown to be equivalent to the consensus models of Borda and Kendall.