Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Program to calculate statistically significant results

Author: Christophe Theron

Date: 10:43:37 01/29/00

Go up one level in this thread


On January 29, 2000 at 11:58:36, Steve Maughan wrote:

>Michael
>
>>Thanks for the offer, although I'm one of those guys who's on a Mac, and so
>>cannot use it.
>
>:-(
>
>>Just a question, does your program take into account draws as well, or just
>>wins and losses?
>
>The binomial distribution works on integers and not fraction so only win / loses
>are accounted for, but one can interpolate the likely scores.
>
>Steve Maughan


I'm not sure I understand. But if you don't take draws into account, then your
results are not OK.

For example, when there is a very high probability of draws, then the actual
error margin is much smaller than normal.

If the probability of draw is 0 (as it seems to be in your program), then your
error margins are going to be overevaluated.


    Christophe



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.