Author: Pete Galati
Date: 18:46:16 01/31/01
Go up one level in this thread
On January 31, 2001 at 20:44:54, Dann Corbit wrote: >On January 31, 2001 at 20:17:17, Bruce Moreland wrote: > >>I expressed very forcefully that a 10-0 result was more valid than a 60-40 >>result. >> >>I've done some experimental tests and it appears that I'm wrong. >> >>I have no idea why. > >Probably the model is too simple. Since chess comes in won/loss/draw, it is >more difficult to achieve an accurate representation, perhaps. > >Your model of the model that you programmed might also be wrong. >;-) > >I use the Mersenne Twister PRNG for random simulations. It has truly excellent >properties. > >With a 10-0 result, the error bars will still be pretty enormous. Even at 60-40 >they will be over 100 ELO, I imagine. I would like to get a copy of your >simulation code to look it over, if you don't mind. (I once ran imaginary coin >flips for 14 days on a PII 350 MHz). What, the percentage of times it came up heads? What were the results? How do you randomly decide between only two sides of a coin? Were there other posibilities like loosing the coin or having it freakishly landing on it's edge and not falling? Pete
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.