Skip to main content

Table 4 Model selection for outcome variable laytime by quartile

From: Factors and predictors of length of stay in offenders diagnosed with schizophrenia - a machine-learning-based approach

VariableBest algorithm/ statistical procedureAccuarcy (%)AUCSensivity (%)Specificity (%)PPV (%)NPV (%)
Victim injured severly/fatallyBagged trees73.60.6470798364
Index crime: (attempted) homicideKNN65.30.5962707853
Victim injury severly/fatally and index crime (attempted) homicideSVM73.60.7178797555