Author: Martin Slowik
Date: 07:45:07 11/10/05
Go up one level in this thread
On November 10, 2005 at 05:40:16, Uri Blass wrote: >On November 10, 2005 at 04:39:11, Joachim Rang wrote: > >> >>> >>> Program Elo + - Games Score Av.Op. Draws >>> >>> 1 Fruit 2.2.1 : 2710 50 49 119 67.6 % 2582 39.5 % >>> 2 Fruit 2.2 : 2691 41 40 174 64.9 % 2584 40.2 % >>> 3 Fritz 9 : 2682 31 31 310 62.4 % 2594 38.4 % >> >>Interesting to see that so far on your rating list there is a difference between >>2.2. and 2.2.1. I'm curious whether it will hold with more games. >> >>Joachim > >I will be surprised if there is no difference between them. >They are different. > >I do not claim to know that 2.2.1 is better and it may be the opposite but it >does not make sense to assume no difference in rating list between programs that >do not behave the same. > >Uri Hi Uri, Even in case 2.2.1 would equal 2.2, I'd be surprised if the ratings were the same. Different Samples Have Different Means (in general) Regards, Martin
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.