ECF Grading Proposals

General discussions about ratings.
Brian Valentine
Posts: 574
Joined: Fri Apr 03, 2009 1:30 pm

Re: ECF Grading Proposals

Post by Brian Valentine » Fri Oct 25, 2019 9:35 am

Mike Gunn wrote:
Thu Oct 24, 2019 5:23 pm
I never understood the argument for recalibration. It was Sean Hewitt's doing and he wrote a paper explaining why it was done and I suppose I should go back and read it, but my problem is this: the idea behind the grading system is that if 2 players with grades 25 apart play a match then one of them should win 3 games out of 4 (i.e. 75% = 50% +25%). But when Sean looked at all the results in the grading system the stronger player was scoring (say) 70%. (The argument is similar for other grading differences and the winning % was always less than it should be.) Now what I don't understand is why this happens - surely there is one dataset of game results and that is used to calculate the grades in the first place - so why aren't the calculated results consistent? I should apologise for bringing this up again but I will be eternally grateful if someone can explain this in a couple of sentences ...
OK, I'll rise to the bait with trepidation, given several of us could not convince the graders last time. You need to make a few sensible assumptions to avoid formulae.

Assume all grades are unbiased estimates of true strength. Some a bit too high, some a bit too low. Assume that there are more average players than top players. Then on every (estimate) grade there are more overperforming more average players than underperforming better players. If all these players then play to their true standard then more (estimated) grades will fall than rise.

That's already more than a couple of sentences, but of course the reasoning implies a reversion to mean and the population of players forms a bell shaped curve, so under-average (estimated) grades will outperform and compensate. However if you only sample results from the higher graded player's point of view then you bias the sample to achieve the Hewitt effect.

Post Reply