Author: KarinsDad
Date: 22:28:51 01/29/99
Go up one level in this thread
On January 29, 1999 at 23:59:55, Peter Kappler wrote: > >I don't understand this statement. The formula is valid regardless of the >rating difference. I think what you are saying is that beyond a certain rating >differential, the win expectancy changes very slowly, and thus the significance >of the rating difference becomes less important. At least I think this is what >you are saying... :-) > > My meaning is as follows: Win expectency for a difference of 1000 points is 0.00315231 (as per Dann's posting). This means that out of 100,000 players with an 1800 ELO (1900 USCF rated players), 315 of them should on average win (i.e. 315 wins or even more draws) against Garry Kasparov in standard tournament times if all 100,000 of them played him. This is total bull. It would be an amazing event if even one of them won (or even drew) against Garry Kasparov in standard tournament times. It should be obvious to the least cynical of people that even if 10000 of those 100,000 players were up and coming players whose ELO should really have been 2100, that they would still be 700 points below Kasparov and the win expentency for those 1000 players (according to the formula) would be 1 in 55. If this was accurate (which also seems really unlikely), then you would expect 182 wins out of these 10000 players. That would mean that even if 10% of the 100,000 players were much stronger, then out of the other 90,000 players, 133 of them would have to win against Kasparov. This is still unreasonable. In other words, the statistical bell curve created by the ELO formula has way too high of probabilities at it's extremes (it starts becoming too high somewhere around the +-300 point level or slightly beyond). KarinsDad :)
This page took 0.01 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.