TableĀ 3

Model selection criteria (log likelihood (LL), Akaike information criterion (AIC) and Bayesian information criterion (BIC)) of the fitted models for sports injury recurrent data*

ModelModel selection criteria
LLAICBIC
Andersen-Gill (A-G)135.0275.9355.6
Frailty134.9277.9378.0
Wei-Lin-Weissfeld total time (WLW-TT) marginal158.1334.2487.6
Prentice-Williams-Petersen gap time (PWP-GT) conditional154.8327.7481.1
  • *The LL, AIC and BIC were not reported due to the small estimated likelihood for the CoxPH model for only the first event.