False positive rate (FPR) of the six variable selection methods with all simulated variables.

<p>100 simulations were used to plot and evaluate the predictive performance of six variable selection methods when the number of total predictors (<i>t</i> = 100 and 200), the number of true predictors (<i>r</i> = 8, 12, 16 and 20) and sample size (<i>n</i> = 50, 100, 200, 300 and 500) change. Left panel: the number of total predictors <i>t</i> = 100; right panel: the number of total predictors <i>t</i> = 200. Six compared variable selection methods: stepwise, stability selection, LASSO, Bolasso, two-stage hybrid and bootstrap ranking procedures.