Skip to main content

Table 1 Mean (SD) of \( {R}_{BS}^2(2) \) for the training sets over 300 simulations

From: Combined performance of screening and variable selection methods in ultra-high dimensional data in predicting time-to-event outcomes

Selection approach Weak signal Strong signal
n = 150 n = 300 n = 150 n = 300
ISIS-LASSO 0.122 (0.109) 0.578 (0.071) 0.335 (0.318) 0.797 (0.071)
ISIS-ALASSO 0.108 (0.108) 0.578 (0.071) 0.337 (0.322) 0.797 (0.071)
ISIS-RSF 0.069 (0.088) 0.564 (0.105) 0.232 (0.284) 0.790 (0.086)
SIS 0.065 (0.085) 0.303 (0.116) 0.114 (0.119) 0.491 (0.177)
SIS-LASSO 0.112 (0.093) 0.306 (0.113) 0.142 (0.119) 0.491 (0.177)
SIS-ALASSO 0.093 (0.092) 0.306 (0.113) 0.137 (0.120) 0.491 (0.177)
SIS-RSF 0.063 (0.082) 0.294 (0.125) 0.097 (0.104) 0.482 (0.178)
PSIS 0.756 (0.116) 0.811 (0.038) 0.642 (0.183) 0.869 (0.047)
PSIS-LASSO 0.875 (0.051) 0.805 (0.037) 0.869 (0.062) 0.874 (0.049)
PSIS-ALASSO 0.874 (0.052) 0.780 (0.042) 0.869 (0.063) 0.849 (0.057)
PSIS-RSF 0.688 (0.088) 0.413 (0.109) 0.655 (0.111) 0.555 (0.167)
LASSO 0.758 (0.138) 0.834 (0.043) 0.787 (0.136) − 0.211 (0.036)
ALASSO 0.583 (0.115) 0.611 (0.058) 0.812 (0.095) 0.815 (0.063)
  1. SD standard deviation