Computer Chess Club Archives




Subject: Re: bayeselo: new Elo-rating tool, applied to CCT7

Author: Uri Blass

Date: 00:03:59 02/15/05

Go up one level in this thread

On February 15, 2005 at 00:37:48, Charles Roberson wrote:

>  Remi,
>    Nice work but, I find it hard to believe that Zappa is > 1500 pts stonger
>  than GnuChess (SuperBot). If we arbitrarily rate zappa at 3000 that puts
>GNUChess at 14xx. Or did I read the table incorrectly?
>  Charles


1)I think that it is typical that the winner is rated too high because
the winner is often lucky.

2)I think that it is possible that the program is wrong in estimating the
rating(it is not an easy problem to estimate rating).

You may test it on other tournament but I suggest that you do not test the
difference in rating from the winner but the difference in rating between
players to see if usually the difference in rating is really 600 when the
program say 600.

You may take tournaments like the olympiad when there are a lot of teams and it
is easy to find players with fide rating 2700 and players with fide rating 2100.


This page took 0.03 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.