Author: Aaron Tay
Date: 10:35:21 06/11/01
Go up one level in this thread
On June 11, 2001 at 12:41:19, Gian-Carlo Pascutto wrote: >On June 11, 2001 at 12:20:23, Leen Ammeraal wrote: > >>Any comments are welcome. > >Peter sent me a similar program which uses a >trinominal distribution (W-L-D). > >Perhaps you should try that, as it's more >accurate. > >GCP I was just wondering, is this trinominal distribution more accurate than the ranges of elo given by Frank Schubert elostat or SSDF ratings?Assuming a rating list of only 2 programs, if the ranges of the 2 programs do not overlap ,it's 95%[or whatever] certain that one is stronger than the other. In this case, which is more accurate? Or is the latter based on a approximation of the normal distribution. Aaron Someone who has only heard of biniomial and normal distribution..
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.