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

[Joern Thyssen]

On Fri, Sep 12, 2003 at 09:59:17AM +0200, address@hidden wrote
> > > It might be useful to do a test of 5-point matches of Woolsey vs.
> > > Snowie, which are probably the most commonly used METs. Or find the two
> > > which diverge the most and compare those, just to see if there is any
> > > noticeable difference.
> 
> I tried  100 5pt 0ply matches woolsey.xml  agains snowie.xml.  Analysing
> with  woolsey at  0ply a  rating discrepancy  of 2193  +-8  resulted (as
> estimated by the "error rate"). Again totally negligible.

Using error rates and the accompanying rating estimates will be biased,
so while it certainly looks like an negligible difference, we need to
use luck adjustment and run a gazillion matches in order to establish
the best MET.

If would be interesting to perform such an experiment at different match
scores, but what would be the value of a result? Will the result depend
on the bot used for the experiment? I could imagine that gnubg would
prefer a gnubg-MET and snowie a snowie-MET, i.e., match equity table
calculated based on rollouts (Ian's experiments).

Jørn

pgp6PONEsUKKM.pgp
Description: PGP signature