Skip to main content

Advertisement

Table 18 Summary of estimated LPLMs as ρ varies

From: Ridge regression estimated linear probability model predictions of O-glycosylation in proteins with structural and sequence data

  ρ 0.05 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.81 0.815 0.82 0.85
In sample SBC 1710 1318 1257 1133 1036 931 878 798 761 749 737 751 723
Variables 12 39 92 91 73 34 50 41 38 54 51 51 39
KS (%) 78.0 89.4 94.1 95.7 95.2 91.3 95.2 95.5 95.7 96.8 96.7 96.6 95.8
Brier Score 0.115 0.062 0.031 0.023 0.025 0.038 0.026 0.026 0.025 0.017 0.018 0.019 0.022
–2×L(·) 1610 1013 547 431 471 664 489 478 463 329 340 354 418
Out of sample Brier Score SNR 1.76 2.55 1.47 1.86 2.18 1.85 3.42 1.59 4.32 3.75 2.00 7.78 3.06