Empirically 1 win + 1 loss ~ 2 draws

Discussion of chess software programming and technical issues.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Modern Times
Posts: 2387
Joined: Thu Jun 07, 2012 9:02 pm

Re: Empirically 1 win + 1 loss ~ 2 draws

Post by Modern Times » Tue Jul 01, 2014 8:22 pm

Laskos wrote:I will check the new BayesElo, Davidson should offer pretty different results from Rao-Kupper, previously used.
There is going to be a new Bayeselo release ?

User avatar
Laskos
Posts: 9410
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: Empirically 1 win + 1 loss ~ 2 draws

Post by Laskos » Tue Jul 01, 2014 8:31 pm

Modern Times wrote:
Laskos wrote:I will check the new BayesElo, Davidson should offer pretty different results from Rao-Kupper, previously used.
There is going to be a new Bayeselo release ?
Daniel Shawul wrote:
Bayeselo uses three different draw models now.
I guess those would be Rao-Kupper (old, wrong one, 1 win + 1 loss = 1 draw), Glenn-David and Davidson.

Post Reply