Moderate-Deviation-Based Inference for Random Degeneration in Paired Rank Lists

Consider a problem where N items (objects or individuals) are judged by assessors using their perceptions of a set of performance criteria, or alternatively by technical devices. In particular, two assessors might rank the items between 1 and N on the basis of relative performance, independently of each other. We can aggregate the rank lists by assigning one if the two assessors agree, and zero otherwise, and we can modify this approach to make it robust against irregularities. In this article, we consider methods and algorithms that can be used to address this problem. We study their theoretical properties in the case of a model based on nonstationary Bernoulli trials, and we report on their numerical properties for both simulated and real data.