Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Tournaments

Author: Enrique Irazoqui

Date: 04:14:33 04/27/98

Go up one level in this thread


On April 27, 1998 at 01:46:22, Jouni Uski wrote:

>I think these results don't confirm SSDF result (F5 superiority)! Why??

They don't contradict them either. In my tournament, each program played
80 games, which means the margin of error is considerable. The SSDF
played 198 games with Fritz 5 and the margin of error is +54 -50. Both
results, theirs and mine, fall well within these margins. In other
words, if we would both play many more games with Fritz 5, results would
tend to get closer.

In my tournament all programs played on equal platforms, while the SSDF
used sometimes unequal platforms. This can make a difference. Aside from
that, we both used the same autoplayer version of Fritz 5.

Enrique




This page took 0.03 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.