Ranking and Selection from Pairwise Comparisons: Empirical Bayes Methods for Citation Analysis

TL;DR

This paper adapts the Bradley and Terry pairwise comparison model using nonparametric empirical Bayes methods to rank and select influential journals based on citation data, providing a new approach to citation analysis.

Contribution

It introduces a novel empirical Bayes approach to ranking journals from pairwise citation comparisons, improving upon existing methods.

Findings

The proposed method effectively ranks journals based on citation flows.

Comparative analysis shows advantages over traditional ranking methods.

Empirical results demonstrate the method's robustness and accuracy.

Abstract

We study the Stigler model of citation flows among journals adapting the pairwise comparison model of Bradley and Terry to do ranking and selection of journal influence based on nonparametric empirical Bayes procedures. Comparisons with several other rankings are made.