[ 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: David Presser
Date: Sunday, 30 November 2014, at 10:19 p.m.

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

I agree that the average should be higher than the median. This is the case for the accumulated data. The fact that it isn't the case for the 2014 data or specific segments supports the claim that the sample is too small to infer from.

As for the skewness, it is easy to compute with modern tools: for 2014 data - 0.46; for accumulated data - 1.58.

Quick explanation - skewness measures the asymmetry of the distribution. Positive skew supports the claim that the tail on the right (high PR) is longer/fatter.

I created a couple of graphs so we can visualize the distribution better. However, I don't know how to present it on html. I am sending those to you (Timothy) in case you are interested and want to follow up.

I also computed skewness for the segments: Long length matches - 0.47; Medium length matches - 1.15; Short length matches - 2.17.

The skewness of the accumulated data is exceptionally high due to two outliers around 18 PR (that were both played in 2013 in the last chance). If you take those out the highest PR in the sample would be 13.

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.