Author: Albert Silver
Date: 22:51:48 02/24/03
Go up one level in this thread
On February 24, 2003 at 11:57:25, Chessfun wrote:
>On February 24, 2003 at 11:46:21, Albert Silver wrote:
>
>>On February 24, 2003 at 10:47:18, Mogens Larsen wrote:
>>
>>>On February 24, 2003 at 09:58:30, Rolf Tueschen wrote:
>>>
>>>>Fun or not, since the programs from different pools (and or generations) do not
>>>>play each other a combined list is misleading. That is the same mistake of the
>>>>SSDF.
>>>
>>>It's only for fun, hence not reliable.
>>
>>I have to agree with Rolf. She should only publish her results until there is a
>>statistically reliable amount of games,
>
>
>Err can you please state what that number would be for us?
100,000
At least.
And verified manually for exact preciseness.
>
>My rating list currently shows Fritz 8 with 98 games and a + - less than some
>programs in the current SSDF list.
But the SSDF isn't statistically scientifically presented in an informationally
non-misleading way.
>
>The same argument can be and was made by Rolf re; The SSDF's posting of Shredder
>7 as #1.
Honest? I think you are just trying to assassinate my character.
>
>
>otherwise people might be misled into
>>believing Fritz 8 is actually 1 Elo point stronger than Deep Fritz 7.
>
>The data is there for people to see, what they choose to make of it is their
>choice.
>
>And it maybe more than that 1 point, I'll get back to you once my + - gets to
>zero which will be, ohhh yea NEVER.
Which brings up another question: what about the programs that are listed with
the same rating? If the general pool of proper generations is tested with a
sufficient number of statistically hand-verified games, say a million or so, it
should be possible to show which is significantly stronger. For scientific
thoroughness. Stalin also lacked scientific thoroughness.
Albert
>
>
>Sarah.
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.