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

BGonline.org Forums

Giants List 2015 - An Analysis of Results

Posted By: Rick Janowski
Date: Thursday, 7 July 2016, at 3:26 a.m.

In Response To: Giants List 2015 - An Analysis of Results (Christian Munk-Christensen)

1. The crude test I used was to calculate the difference in actual y-axis value (average points per ballot) with that predicted by the trend line, and then calculate the standard deviation of the sample set. Any value more than 3 standard deviations away from the predicted value was considered as an outlier (the normal set of results were all contained within a +/- 2*SD band). The 4 outliers were 4.2, 6.7, 6.8 6.9 and 7.2 standard deviations away from their predicted values.

2. The identity of each position on the x-axis of the graph may be identified from the 2015 listing of Giants.

3. I think in future Giants Lists it would be sensible to either remove or at least moderate results (perhaps adjust results based on number of ballots and predicted average score using the trend line for the normal results).

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.