Skip to main content

Table 3 Model performance measures according to odds ratio, number, and prevalence of simulated predictors

From: Predictor characteristics necessary for building a clinically useful risk prediction model: a simulation study

Simulated predictor characteristics Model performance measures  
OR of simulated predictors Number of simulated predictors added to original model Prevalence of simulated predictors Proportion of population (%) with informative likelihood ratio a Proportion of population (%) assigned to clinically distinct risk group b AUC Nagelkerke’s r2 (%)
2 3 10 % 0.0 27.2 0.71 10.0
2 3 20 % 0.0 29.9 0.73 11.7
2 3 40 % 0.0 34.8 0.74 12.9
2 5 10 % 0.0 28.9 0.73 11.8
2 5 20 % 0.0 33.3 0.75 14.6
2 5 40 % 0.0 39.2 0.77 16.6
6 3 10 % 0.0 54.4 0.83 29.4
6 3 20 % 63.6 63.6 0.87 37.1
6 3 40 % 70.2 70.0 0.88 37.1
6 5 10 % 66.9 66.9 0.88 40.6
6 5 20 % 72.0 72.0 0.92 50.7
6 5 40 % 73.8 73.8 0.93 51.2
  1. aDefined as the proportion of the population classified into a stratum with a likelihood ratio <0.10 or >10.0
  2. bDefined as the proportion of the population classified into a stratum with predicted risk meaningfully different than the baseline rate of pre-eclampsia in the population (<0.03 or >0.15)