Computing a ranking network with confidence bounds from a graph-based Beta random field

F. Hsieh, M.P. McAssey, B. McCowan

Research output: Contribution to JournalArticleAcademicpeer-review

137 Downloads (Pure)


We address two largely overlooked, fundamental issues in computing a ranking hierarchy within a society: which information in the network is relevant, and what effect chance has on the hierarchy. To properly account for uncertainty from limited data, we construct a random field in a matrix form having entry-wise posterior Beta distributions based on a graph of pairwise conflict outcomes. To evaluate relevant network information using information transitivity, another random matrix of synthesized transitive dominance odds is computed collectively along observed dominance paths. These two matrices are coupled together to fuse both direct and indirect dominance information. An ensemble of realizations of this fused random matrix facilitates an ensemble of optimal ranking networks by means of simulated annealing. Conditional statistical inferences regarding network features are derived, manifesting the effect of uncertainty. Our computational approach is suitable for large graphs of pairwise conflict outcomes, and can accommodate tremendous data heterogeneity-a typical feature in such studies. We also demonstrate the infeasibility of the classical maximum-likelihood approach, and expose the mechanistic flaws that stem from completely ignoring relevant information residing in the graph. We analyse two real datasets of decisive conflict outcomes, the first involving college football teams, and the second involving an adult rhesus macaque society in captivity. © 2011 The Royal Society.
Original languageEnglish
Pages (from-to)3590-3612
Number of pages23
JournalProceedings of the Royal Society. Series A, Mathematical, physical and engineering sciences
Issue number2136
Early online date3 Aug 2011
Publication statusPublished - 2011


Dive into the research topics of 'Computing a ranking network with confidence bounds from a graph-based Beta random field'. Together they form a unique fingerprint.

Cite this