RE: [Bug-gnubg] Re: The importance of METs

[kvandoel]

On Fri, 12  Sep 2003 19:40:28, someone who doesn't  want to be mentioned
in the same breath as me wrote:

>> pointed out that the Woolsey table at 4-away 3-away looked completely
>> wrong compared to the Snowie table for example. Many othger scores may
>> be quite correct so testing all the scores may dilute the differences
>> one would feel. How about trying a series of match games where the score
>> is specifically 4-away 3-away and see how big a difference it makes?

>The  mwc at  a  match  score is  never  used at  that  match score,  or
>shouldn't  be.   (This  is a  problem  with  some  work of  Ortega  and
>Kleinman. I don't know whether they correct this in their book on cubes
>in match play.) The entry at 3-away 4-away should affect cube decisions
>at 4-away 4-away greatly, as well as 4-away 5-away and 3-away 5-away.

100 4pt matches between woolsey.xml and snowie.xml at 0ply resulted in a
rating difference of 2 +- 1  points. The maximum playing difference in a
match (error rates converted to rating points) was 49.

Kees