Skip to main content
. Author manuscript; available in PMC: 2016 Sep 7.
Published in final edited form as: Biometrics. 2016 Feb 4;72(3):888–896. doi: 10.1111/biom.12480

Table 2.

Simulation studies for three biomarkers. Results are based on the completed studies from 1000 simulated datasets. The empirical mean (empirical standard error) are given for each estimator of the β, excluding the intercept.

True ROC(0.2) True β β̂RB
nD = n = 400, mD = m = 200

0.55
[0.130.560.48]
[0.14(0.11)0.57(0.12)0.49(0.09)]
0.60
[0.770.180.31]
[0.79(0.13)0.18(0.12)0.31(0.10)]
0.65
[1.13-0.040.22]
[1.14(0.14)-0.03(0.12)0.22(0.10)]
0.70
[1.44-0.220.13]
[1.46(0.14)-0.22(0.12)0.14(0.10)]

nD = n = 200, mD = m = 100

0.55
[0.130.560.48]
[0.12(0.17)0.58(0.17)0.49(0.13)]
0.60
[0.770.180.31]
[0.79(0.18)0.19(0.16)0.32(0.14)]
0.65
[1.13-0.040.22]
[1.16(0.20)-0.03(0.17)0.22(0.14)]
0.70
[1.44-0.220.13]
[1.48(0.21)-0.23(0.18)0.14(0.15)]

nD = n = 100, mD = m = 50

0.55
[0.130.560.48]
[0.12(0.26)0.61(0.25)0.50(0.19)]
0.60
[0.770.180.31]
[0.81(0.27)0.20(0.25)0.32(0.20)]
0.65
[1.13-0.040.22]
[1.19(0.29)-0.03(0.25)0.23(0.20)]
0.70
[1.44-0.220.13]
[1.54(0.32)-0.23(0.27)0.14(0.21)]

nD = n = 50, mD = m = 25

0.55
[0.130.560.48]
[0.14(0.38)0.65(0.39)0.54(0.31)]
0.60
[0.770.180.31]
[0.86(0.42)0.21(0.38)0.35(0.30)]
0.65
[1.13-0.040.22]
[1.27(0.45)-0.04(0.40)0.24(0.32)]
0.70
[1.44-0.220.13]
[1.63(0.75)-0.23(0.62)0.13(0.50)]