Talk:Pairwise comparison (psychology)

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

Applications (of Pairwise comparison)[edit]

I wish to draw to editors' attention to this Wipedia article that is based on pairwise comparisons: Potentially All Pairwise RanKings of all possible Alternatives (PAPRIKA). I recently re-wrote this article, including satisfying the notability requirements, and it was reinstated (undeleted). I wonder if perhaps the editors of "Pairwise comparison" might consider linking to this article and/or discussing the PAPRIKA method as another application of pairwise comparisons? Paulwizard (talk) 07:20, 9 October 2010 (UTC)[reply]

Elo's Chess Algorithm[edit]

Have you considered adding information about Elo's chess ranking algorithm, since it's such a popular ranking method for many sports based on pairwise comparisons? Elo basically adopted the Bradley-Terry model (actually he started by using the Gaussian distribution as Thurstone did). Elo used a simply update rule rather than applying maximum likelihood to estimate the skill levels. Paulipu (talk) 04:43, 11 February 2011 (UTC)[reply]

Notation[edit]

Do you have to use the notation "If xPy and yIz, then xPz"? To a newcomer, it would be easier to read if it were written "If x > y and y = z, then x > z" 71.167.73.5 (talk) 16:15, 19 October 2014 (UTC)[reply]