Talk:Elo rating system

From Wikipedia, the free encyclopedia
Jump to: navigation, search

          This article is of interest to the following WikiProjects:
WikiProject Chess (Rated C-class, Top-importance)
WikiProject icon This article is within the scope of WikiProject Chess, a collaborative effort to improve the coverage of Chess on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
C-Class article C  This article has been rated as C-Class on the project's quality scale.
 Top  This article has been rated as Top-importance on the project's importance scale.
WikiProject Board and table games (Rated C-class, Mid-importance)
WikiProject icon This article is part of WikiProject Board and table games, an attempt to better organize information in articles related to board games and tabletop games. If you would like to participate, you can edit the article attached to this page, or visit the project page, where you can join the project and/or contribute to the discussion.
C-Class article C  This article has been rated as C-Class on the quality scale.
 Mid  This article has been rated as Mid-importance on the importance scale.

Effect of number of games played on strict zero sum[edit]

Because the number of games played by each player effects the gain and loss of each, points are not strictly transfered from one player to another. A new number is created for each player, though it has the mystical quality of being approximately zero sum. (talk) 08:18, 5 August 2014 (UTC)

"Ratings inflation"[edit]

I have just noticed that this article uses "ratings inflation" instead of "rating inflation". Google tells me that the former is used more than the latter, and I have seen both spellings used in respectable sources. Are both grammatically correct? Toccata quarta (talk) 22:00, 30 April 2013 (UTC)

It's very late in coming, but I thought your question deserves some response. As far as I know, both expressions are grammatical in English. Quale (talk) 15:45, 25 June 2013 (UTC)

Tweaks to improve readability of math formulae section.[edit]

I tweaked some formatting (layout) in the Performance_rating section with mathematical formulae because I had trouble reading the section because of tight spacing between lines. My first attempt yesterday was okay but unorthodox. Today I found an MOS:MATH section--Using Latex Markup--with a better solution, and I made changes consistent with that MOS section. - Great article btw - I'm a Class D player trying to learn more. ;o) Mark D Worthen PsyD 04:21, 30 April 2014 (UTC)

Condorcet method[edit]

I know it's not "voting", but could this be considered a Condorcet method, since if Alice always beats everyone else, she is placed at the top of the ranking list? (talk) 13:55, 9 October 2014 (UTC)

  • Condorcet methods are a category of voting systems while the Elo rating system is not a voting method or even a contest. A statement like "The Elo rating system is a Condorcet method" would, in my view, qualify as not even wrong since the term "Condorcet method" simply doesn't apply to rating systems. Also I should mention that even if Alice beats everyone else in the system there is no theoretical guarantee that she would top the rating list. If Bob loses only one game, to Alice, but remains a much more active player who plays lots more games and wins against everyone except Alice, his rating will creep up for every win and eventually surpass Alice's rating. Sjakkalle (Check!) 19:57, 11 October 2014 (UTC)
How is voting not a rating system? Are they not both in the category of Pairwise comparison? (talk) 15:53, 19 October 2014 (UTC)
Elections are a contest that determine a winner based on the popularity of the candidates. The rating system is not a contest, its purpose is to estimate the strength of players based on their results in tournament games. Sjakkalle (Check!) 07:27, 27 October 2014 (UTC)

ELO or Elo?[edit]

For quite a few years, the system was formerly known as the ELO system, even though it was named after professor A. Elo. Bubba73 You talkin' to me? 08:56, 25 November 2014 (UTC)

Calculating the Rating Difference table[edit]

The standard normal distribution, with mean value μ = 0 and standard deviation σ = 1, in x = 2.17 equals to 98.500%. This is the first value in the 99% category. The corresponding rating in Fide table 8.1b [1] is 620. Therefore the standard deviation employed in the table equals to 620 / 2.17 = 2000 / 7. The Elo table contains a few irregularities. A more accurate expectation of 620 equals to 98.4997%, which falls into the 98% range. The table assigns 344 to expectation 88%. However the expectation due to the normal distribution is 88.5705%, which is clearly in the 89%. Needed are references to the construction of this table in order to explain the underlying calculation.

(Clpippel (talk) 14:00, 13 January 2015 (UTC))

  1. ^ "FIDE Online. FIDE Rating Regulations effective from 1 July 2014". 2014-07-01. Retrieved 2014-07-01.