Skip to main content

Table 4 Logistic regression prediction performance results across 100 cross-validations

From: Evaluating the clinical utility of an easily applicable prediction model of suicide attempts, newly developed and validated with a general community sample of adults

Predictor

Min

1st Qu.

Mean

Median

3rd Qu.

Max

PR AUC

0.028

0.074

0.132

0.106

0.163

0.436

ROC AUC

0.644

0.771

0.805

0.800

0.846

0.916

ICI

0.003

0.006

0.008

0.008

0.010

0.018

  1. Note. Min = minimum; 1st Qu. = 25% quantile; 3rd Qu. = 75% quantile; Max = maximum; PR AUC = area under the precision-recall curve; ROC AUC = area under the receiver operating characteristic curve; for both, a value of 1 represents perfect discrimination; ICI = Integrated Calibration Index; a value of 0 for the ICI represents perfect calibration