AFL Player Correlations

Player Correlations


Viewing Correlations for Tom Mitchell
Mitch Lewis2175.001.000
Dallas Willsmore2110.001.000
Marc Pittonet2156.001.000
Conor Glass10262.800.730
Jonathon Ceglar11378.890.604
Blake Hardwick42210.340.440
Ryan Schoenmakers20173.050.436
David Mirra7286.330.434
Paul Puopolo35212.660.385
Teia Miles12191.300.349
Kurt Heatherley460.500.347
Will Langford25122.000.253
Ben Stratton31126.450.233
Taylor Duryea3267.050.142
Jonathan ORourke3101.330.136
Jaeger OMeara2765.260.106
Ryan Burton4237.730.078
Isaac Smith4622.440.042
James Worpel1123.060.037
Ben McEvoy414.300.009
Jack Gunston45-12.43-0.021
Harry Morrison22-43.10-0.078
Kaiden Brand27-31.08-0.094
Daniel Howe35-56.99-0.103
Brendan Whitecross14-48.00-0.107
Liam Shiels44-67.80-0.110
Tim OBrien28-90.13-0.137
Ricky Henderson40-71.48-0.154
Luke Breust45-122.21-0.170
James Frawley27-69.82-0.182
Jarryd Roughead44-95.15-0.193
Shaun Burgoyne38-105.08-0.262
James Sicily35-203.46-0.276
Jarman Impey24-151.28-0.323
Conor Nash5-179.95-0.509
Cyril Rioli10-96.89-0.573
James Cousins6-200.00-0.718
Grant Birchall4-63.08-0.767

Correlation is used to define a relationship between two variables, with a perfect positive correlation indicated by 1.0 and a perfect negative correlation being assigned a value of -1.0. Correlation however does not indicate the extent to which the two variables change together. Because of this, it’s important to understand the co-variance between the two variables also.

The chart above shows 4 theoretical player’s scores over 6 games. Each of Player’s B, C & D have high correlations to Player A indicating they have a perfect (or near perfect) positive correlation. However, it’s clear from the chart that if you were expecting Player A to have a high scoring game, the best player to stack him with would be Player D as he scores significantly better than the others when Player A scores higher. Correlation does not give us any insight into this and it’s by understanding co-variance that we can take advantage of this.

Player Correlation Co-Variance
Player B 1.000 350
Player C 1.000 438
Player D 0.980 980

Looking at the numbers we can see that Player D’s correlation is in fact slightly less than the other players, however, his co-variance is much larger. In simple terms, the co-variance indicates how two variables vary together and as such for fantasy sports the larger the value the better.

So, we can see from this simple example that correlation should always be used in conjunction with co-variance as correlation is only half the story.