WTC HbE performance 1

This site uses cookies. By continuing to browse this site, you are agreeing to our Cookie Policy.

The latest issue of the 9th Scroll is here! You can read all about it in the news.

Looking at HbE performance relative to team placement.

Left Graphs: Raw points vs. Team Placement

Right Graphs: HbE % of Team Score vs. Team Placement (basically, factoring out team point total covariation).

Upper Graphs: As above with all data points

Lower Graphs: As above with 36th place Slovakia's HbE removed (a priori and ad hoc posteriori justifications: a priori - brand new player who was there solely to fill the team, had no tournament experience at all. Ad hoc posteriori - 14% of the explanatory power of HbE % is due to that one data point, so it's seriously different than the other points).

Takeaway: I'm not interested in significance here, only explanatory power (although it would be reasonably easy to assess significance). Correcting for total team points (ie, looking at HbE performance relative to team mates) reduces explanatory power by a huge amount - it goes from explaining 67% of the variance to 20%! That means that the real story here isn't HbE, it's total team points. (Which of course it is - there's a reason this needed to be corrected for - autocorrelation is an issue).