Skip to main content



Bayes Rule to Find Athletes Who Dope

Around 10 years ago, sports scientists started using Bayes rule to predict whether an athlete was using an illegal substance called erythropoietin to enhance his performance or not; this was called the Athletic Biological Passport (ABP), since it was thought it would help prevent cheating because of its low variability. A study that came out in 2011 determine that this method was very effective at detecting athletes cheating, but a 2009 study showed that altitude training can affect the ABP results and because of this there could be some accuracy variability, but given some modifications it can be considered very accurate anyways.

A few months ago a big database containing the information of more than 12,000 blood tests of different athletes was leaked, and many world-known athletes are featured in that list with abnormal blood samples that could indicate the use of exogenous substances to improve their performance, but the IAAF is not doing anything about it, suggesting that even though the method is reliable, they’re not fully implementing it.

This is relevant to the class because it’s a real world application of Bayes Rule, which is necessary in this case because there’s no other reliable method to detect some illicit substances.

Sources:

http://www.newyorker.com/news/sporting-scene/using-math-to-catch-athletes-who-dope

http://www.bbc.com/sport/athletics/33749208

Comments

Leave a Reply

Blogging Calendar

November 2015
M T W T F S S
 1
2345678
9101112131415
16171819202122
23242526272829
30  

Archives