| λ | μY | μx | AUCtrue | MW* | R* | P* | |
0 |
0 |
0.25 |
0.570 |
Bias(×103) 95% Cl |
−26 (-29, -22) |
- 14 (-19, -10) |
0 (-6,5) |
| MSE(×104) 95% Cl |
23 (20, 26) |
30 (26,34) |
41 (35,46) |
||||
| Coverage (%) 95% Cl |
90.3 (87.5,93.1) |
94.5 (92.6, 96.5) |
95.3 (93.5, 97.1) |
||||
0 |
0 |
0.5 |
0.638 |
Bias(×103) 95% Cl |
- 53 (-56, -51) |
- 31 (-34, -28) |
2 (-2,7) |
| MSE(×104) 95% Cl |
45 (40,49) |
38 (33,43) |
37 (40,53) |
||||
| Coverage (%) 95% Cl |
72.5 (68.3,76.8) |
91.4 (88.8, 93.9) |
95.7 (93.9, 97.6) |
||||
0 |
0 |
1 |
0.76 |
Bias(×103) 95% Cl |
- 111 (-114, -108) |
- 72 (-76, -67) |
17 (11,24) |
| MSE(×104) 95% Cl |
138 (131, 146) |
83 (75,90) |
67 (58,75) |
||||
| Coverage (%) 95% Cl |
12.9 (10.3, 15.6) |
66.1 (61.8, 70.5) |
96.9 (95.2, 98.7) |
); R: Reiser’s (2000) method; P: probit method.** Simulation III was run 100 times. Each time, we generated 1000 simulated data sets. Each data set consists of 100 cases and 100 controls. each subject provides two
replicate biomaker scores. Both true values and random errors were generated from log normal distributions with
from simulation III**.