ELTE logo ELTE Eötvös Loránd University
ANNALES Universitatis Scientiarum Budapestinensis de Rolando Eötvös Nominatae
Sectio Computatorica

Volumes » Volume 36 (2012)

https://doi.org/10.71352/ac.36.143

EM algorithms for generalized Bradley–Terry models

Villő Csiszár

Abstract. The Bradley–Terry model and its generalizations are popular models for paired (or multiple) comparisons of individuals or teams. The literature describes several approaches to maximum likelihood estimation of the parameters. Here we propose the use of the EM scheme, we study its convergence properties, and compare it with previous algorithms.

Full text PDF
Journal cover