A computationally intensive ranking system for paired comparison data

Abstract In this paper, we introduce a new ranking system where the data are preferences resulting from paired comparisons. When direct preferences are missing or unclear, then preferences are determined through indirect comparisons. Given that a ranking of n subjects implies ( 2 n ) paired preferences, the resultant computational problem is the determination of an optimal ranking where the agreement between the implied preferences via the ranking and the data preferences is maximized. Comparisons are carried out via simulation studies where the proposed rankings outperform Bradley–Terry in a particular predictive comparison.

[1]  M. Newman,et al.  A network-based ranking system for US college football , 2005, physics/0505169.

[2]  David Mease,et al.  A Penalized Maximum Likelihood Approach for the Ranking of College Football Teams Independent of Victory Margins , 2003 .

[3]  Barrow Daniel,et al.  Ranking rankings: an empirical comparison of the predictive power of sports ranking methods , 2013 .

[4]  Peter J. Huber,et al.  Pairwise Comparison and Ranking in Tournaments , 1963 .

[5]  J. Gandar,et al.  The home field advantage revisited: a search for the bias in other sports betting markets , 2001 .

[6]  M. Glickman.  Parameter Estimation in Large Dynamic Paired Comparison Experiments , 1999 .

[7]  Shane T. Jensen.  A Statistician Reads the Sports Pages , 2011 .

[8]  L. Thurstone.  A law of comparative judgment. , 1994 .

[9]  R. Plackett.  The Analysis of Permutations , 1975 .

[10]  C. Chen,et al.  A Bayes-type estimator for the Bradley-Terry model for paired comparison , 1984 .

[11]  Manuela Cattelan,et al.  Models for Paired Comparison Data: A Review with Emphasis on Dependent Data , 2012, 1210.1016.

[12]  Tim B. Swartz,et al.  Journal of Quantitative Analysis in Sports Ups and Downs : Team Performance in Best-of-Seven Playoff Series , 2012 .

[13]  Tom Leonard,et al.  An Alternative Bayesian Approach to the Bradley-Terry Model for Paired Comparisons , 1977 .

[14]  Tim B. Swartz,et al.  New Insights Involving the Home Team Advantage , 2014 .

[15]  Constantino Tsallis,et al.  Optimization by Simulated Annealing: Recent Progress , 1995 .

[16]  Xiaoyu Qian,et al.  Ranking Systems Used in Gaming Assessments and/or Competitive Games , 2015 .

[17]  Ehl Emile Aarts,et al.  Simulated annealing and Boltzmann machines , 2003 .

[18]  Kathryn A. Dowsland,et al.  Simulated Annealing , 1989, Encyclopedia of GIS.

[19]  David HARViLLE,et al.  The Use of Linear-Model Methodology to Rate High School or College Football Teams , 1977 .

[20]  D. Harville,et al.  The Selection or Seeding of College Basketball or Football Teams for Postseason Competition , 2003 .

[21]  Mark E. Glickman,et al.  Dynamic paired comparison models with stochastic variances , 2001 .

[22]  R. Davidson.  On Extending the Bradley-Terry Model to Accommodate Ties in Paired Comparison Experiments , 1970 .

[23]  Arnaud Doucet,et al.  Efficient Bayesian Inference for Generalized Bradley–Terry Models , 2010, 1011.1761.

[24]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .