On 13 Mar 2002 03:40:24 -0800, [EMAIL PROTECTED] (John Smith)
wrote:

> I have what I hope is a simple theoretical question to resolve an
> argument:
> 
> The problem concerns finishing position at the end of round-robin
> chess competition.
> 
> If competitor A has probability Pa of finishing in the top half of the
> league table, and competitor B has Pb, what is the probability that A
> finishes higher than B ?

Not just simple, but simplistic.  That is, I think you 
assume a most simplistic model, where a single 
'quality'  number implies who is going to win.
That is in contrast to the real world, where 
A>B and  B>C  can  be consistent with C>A.

But even that is not enough to answer the question
that you are asking.  How well does the number
predict the outcome?  

- I remember one EXTREME year of college 
basketball-conference results for my local team (Pitt).  
The 10 teams exhibited 8 'levels-of-performance' 
during the home-and-home   competitions.  
That is, the favored team won every time.  
The home team won each game in the couple of
instances where the ranks were tied.

(That's the way I remember it, anyway.)

-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to