Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Statistical data about draws and rating differences

Author: Andrew Dados

Date: 06:24:42 02/05/01

Go up one level in this thread


On February 04, 2001 at 18:41:45, Walter Koroljow wrote:

>On February 04, 2001 at 14:16:19, Vincent Diepeveen wrote:
>
>>On February 04, 2001 at 14:11:19, Hermano Ecuadoriano wrote:
>>
>>>On February 04, 2001 at 13:58:11, Andrew Dados wrote:
>>>
>>>>
>>>>I decided to find out 'true chance' of draw outcome from real games.
>>>>The below is summarized output from my twic game files.
>>>>Rdiff means difference of players ratings in the (range, range+25).
>>>>Integrestingly around range of 0 draws approaches 50% and better won about 25%.
>>>>
>>>>Now if you take 2 tosses of coin you'll get total score of 2 heads in 25%, 1
>>>>head in 50% and 0 heads in 25%...
>>>>
>>>>
>>>> files: 176      games: 170464   decisive (counted) : 128803
>>>>
>>>>Rdiff+  games   %draws  %better won
>>>>=======================================
>>>>0       14480   48.82   25.67
>>>>25      15365   46.57   31.45
>>>>50      15784   44.60   35.52
>>>>75      15429   41.80   39.62
>>>>100     14092   38.68   44.26
>>>>125     12121   35.08   49.18
>>>>150     9926    31.92   54.47
>>>>175     8129    28.34   58.89
>>>>200     6478    25.39   63.71
>>>>225     4707    22.82   67.94
>>>>250     3443    20.65   69.82
>>>>275     2575    18.45   73.67
>>>>300     1879    15.59   77.38
>>>>325     1370    15.62   78.83
>>>>350     970     10.52   85.46
>>>>375     687     9.32    86.90
>>>>400     453     7.06    89.18
>>>>
>>>>Is one chess game statistically equivalent of 2 coin tosses? :)
>>>>
>>>>-Andrew-
>>>
>>>This is good data to look at.
>>>But you need another dimension: either rating mean, or the rating of the
>>>higher rated player. I suggest the mean.
>>>Then, having a table like the above for every rating level, somebody can
>>>curve-fit the thing.
>>>
>>>These databases are something else that ELO didn't have.
>>
>>Exactly, there is a big difference from below 2000 and above 2000
>>as K factor gets for FIDE rating from 25 down to 15 down to 10.
>>
>>Nevertheless good work from Andrew!!
>
>I also agree.
>
>But thank you for great data.
>
>What are "twic files"?  Is this all human data?
>
>Cheers,
>
>Walter

'The Win at Chess' url: http://www.chesscenter.com/twic/twic.html

Every week they put together a very sensible pgn file of recent events.
Since I don't have a decent database around here, I choose twics files from last
3 years+. I expect very few duplicates there and no bogus data. And about 2/3 of
game scores have rating info assigned. And yes, those games are all human-human
(with few human-comp exceptions and maybe last wccc included, not sure of that).
Good and bad is structure of ratings - most games published there are between
players above 2200 elo.

-Andrew-



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.