[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Win Rate as a function of PR difference - XG Feature

Posted By: Maik Stiebler
Date: Friday, 21 August 2015, at 6:32 a.m.

In Response To: Win Rate as a function of PR difference - XG Feature (AdamStocks)

Sorry to bother you, but this sounds so interesting that I'll insist on trying to understand it, and I'm nowhere near yet.

An insight that I took away from studying a certain article about ratings in backgammon is that a player who enters a perfectly rated population but is underrated himself will have to expect to stay underrated, and vice versa. That is the same with or without the ramp formula, only the ramp formula reduces the half-life time of the expected deviation from the true rating while adding a larger amount of noise.

Am I wrong about this? And if I'm not, can you help me harmonize it with what you wrote in this thread? Were you just assuming that new players are typically stronger than their initial rating of 1500? But wouldn't that lead to a global rating deflation?

Messages In This Thread

 

Post Response

Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:

 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.