Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: A question about statistics...

Author: Peter Fendrich

Date: 05:05:34 01/12/04

Go up one level in this thread


On January 09, 2004 at 13:26:17, Dieter Buerssner wrote:

>On January 09, 2004 at 08:53:58, Peter Fendrich wrote:
>
>>On January 07, 2004 at 12:23:00, Dieter Buerssner wrote:

- snip -
>... About the Elo formula ("400LG").
>Actually I thought until very recent, that the Elo formulas use a normal
>distribution (and Elo's original approach did). Recently I learned (from
>Glickman's (sp?) papers)  that USCF and FIDE use the logistic distribution
>instead (the LG formula). I am still puzzled. There is only very little
>differnece between the two -it can be seen in the tails, however (when rating
>difference is huge - say over 400).

I know nothing about this, I only once read the original papers from Dr Elo and
haven't been updated about what's happened since then...
I can tell you that the both formulas aren't equivalent, at least I can't see
how to reduce the Elo original to the "400LG" type.
Glickman has done a considerable amount of work within this domain and maybe he
have some argumentation why one is better than the other. IMO the differrences
are so small between the formulas that other error sources are more dominant and
interesting.

Regards,
Peter



This page took 0.02 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.