Author: Uri Blass
Date: 10:33:25 12/24/00
Go up one level in this thread
On December 24, 2000 at 13:11:49, Christophe Theron wrote: >On December 24, 2000 at 09:09:27, Jeroen Noomen wrote: > >>My congratulations to Vishy Anand, for winning the >>FIDE World Championship 2000! >> >>3,5-0,5 in the final against Shirov, that leaves no >>discussion whatsoever. Anand was the best, remained >>unbeaten and scored a clear victory in the final. >>Well done! >> >>Jeroen > > >I am still absolutely amazed that a World Championship can be decided this way. > >A score of 3.5-0.5 is not statistically significant, not even with a low >confidence. The question is if all the assumptions about comp-comp games are similiar in human-human games. I think that the number of draws in human-human games is bigger and it make the result of 3.5-.5 more significant. Chess is also not the same as dropping a coin. There are preperation of both sides and if one side did better preperations it cannot be described as luck. We need a better model. > >It is now clear, at least amongst the experienced computers chess operators, >that such a result means NOTHING. I think that nothing is not accurate. If you decide that the winner is better you will still be correct in most of the cases. If you can guess the better program and if you are correct in 55% or 60% of the cases it means more than nothing. Uri
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.