veloclinic.com
A Bayesian approach to boost individual anti-doping classification accuracy by transverse monitoring of the athlete network - veloclinic
Purpose: To demonstrate a Bayesian approach utilizing the athlete network to boost the positive predictive value of individual doping classifications. Study Design and Methods: Five data-sets of 10,000 individuals and their networks were simulated and statistically analyzed in R. Background prevalence (BP) of 10%, 20%, 30%, 40%, and 50% was chosen to cover the range …