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

BGonline.org Forums

Data regarding ABT open players' PR - Part 2

Posted By: Michael Sullivan
Date: Tuesday, 2 December 2014, at 6:56 p.m.

In Response To: Data regarding ABT open players' PR - Part 2 (David Presser)

the lower SD for longer matches doesn't surprise me at all. If we view player's "true skill level" as a probability distribution of PRs centered around some number with some variance, then we would expect longer matches to have PRs closer to the center on average, as there are more decisions, and thus more time for the playing level to regress to the mean.

This should apply within a population of players as well. A shorter match is a smaller sample size, so big outliers are more likely. As player who averages around 7, I've never played a match of 21 points that I analyzed under 4 PR, but I've played plenty of 5 pointers less than that, and some 1-3 pointers under 1. I've also played some 1-3 pointers >20.

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.