Skip to main content

Table 2 Retained predictors and associated areas under the ROC curves for the models for each course

From: Models to predict injury, physical fitness failure and attrition in recruit training: a retrospective cohort study

OutcomeCourseRetained predictorsNagelkerke R2AUC
Any injury28-daySex, Age, Init-SU, Init-shuttlea0.060.63
80-daySex, Age, BMI, Init-SU, Init-shuttlea0.050.60
Overuse injury28-daySex, Age, Init-SU, Init-shuttlea0.050.63
80-daySex, Age, BMI, Init-shuttlea0.060.61
Stress fracture28-day(No model: only 1 stress fracture)
80-dayHt, Age, Init-shuttle0.050.69
Neuromuscular injury28-daySex, Age, Init-SU, Init-shuttlea0.070.64
80-daySex, Age, BMI, Init-shuttlea0.050.60
Traumatic injury28-daySex, Age0.020.59
80-daySex, Age, BMI, Init-SUa, Init-shuttlea0.020.57
Final BFA battery failure28-dayAge, Wt, Init-PUa, Init-SUa, Init-shuttlea0.100.64
80-dayHt, Wt, Init-PUa, Init-SUa, Init-shuttlea0.070.64
  1. AUC area under the ROC curve, Init-PU push-up repetitions obtained upon arrival at the basic training site, Init-SU sit-up repetitions obtained upon arrival at the basic training site, Init-shuttle shuttle run level obtained upon arrival at the basic training sitem, Ht height in cm, Wt weight in kg, BMI Body mass index in kg/m2, BFA Basic Fitness Assessment, afailure. dichotomized pass/fail version of the predictor variable. -. No data