Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Comments of latest SSDF list

Author: Martin Schubert

Date: 03:17:45 05/26/02

Go up one level in this thread


On May 26, 2002 at 05:02:43, Uri Blass wrote:

>On May 26, 2002 at 02:46:42, Martin Schubert wrote:
>
>>>That means that at this time Fritz7 has the most probability to be the best. So
>>>it must be listed as number one.
>>
>>That's not true. There is no probability for Fritz7 being the best. You can't
>>calculate any probability for that because the statistical assumptions are that
>>the ratings are unknown but solid.
>
>We can talk about probabilities because we do not know and the question is what
>is our chances to be correct in guessing.

You're wrong. We don't know the true rating. But there are now probabilities for
that. Statistically we have assumptions of solid unknown ratings. The
probabiilities are lying in the results of the games. After having finished the
games there is no chance anymore (is "chance" the right english word in this
context? I mean the german "Zufall"). So you can't talk about probabilities in
this context.

>
>Before playing games we need to have some assumptions.
>
>A possible assumption is to say that the rating are fixed but are taken from
>some normal distribution with known parameters.
>
>After defining the exact assumptions that we have, it is possible to calculate
>probabilities based on the knowledge that we have.
>
No, we can't calculate probabilities for the rating which is fixed. We can
calculate some confidence intervalls. Before playing the games we can say a
confidence intervall has a probability of 95%. Because the borders of the
intervall are depending on chance. After having played the games and after
having calculated borders, you can't talk about probabilities for the specific
intervall.
>Uri

Martin

P.S.: I'm discussing this topic at the moment with Thomas Kantke at CSS-Forum.



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.