Table 2 The mean and Monte Carlo standard error in parentheses of the bias and RMSE of the cutoff when targeting a specificity of 0.995. The method(s) with minimal bias and RMSE in each scenario or equivalent after rounding are bolded
Scenario A | Scenario B | |||
|---|---|---|---|---|
n=50 | n=200 | n=50 | n=200 | |
Bias of cutoff | ||||
Empirical | -0.93 (0.0049) | -0.37 (0.0035) | -3.60 (0.0327) | -1.77 (0.0249) |
Normal | -1.74 (0.0027) | -1.70 (0.0014) | -6.26 (0.0158) | -5.71 (0.0112) |
Log Normal | -1.34 (0.0030) | -1.36 (0.0015) | -6.72 (0.0070) | -6.79 (0.0032) |
MAD | -2.68 (0.0010) | -2.68 (0.0005) | -9.08 (0.0013) | -9.09 (0.0006) |
Log MAD | -2.00 (0.0025) | -2.02 (0.0012) | -8.41 (0.0031) | -8.47 (0.0014) |
Pareto 0.9 | -0.15 (0.0064) | -0.02 (0.0033) | -3.03 (0.0309) | -2.97 (0.0154) |
Pareto 0.95 | -0.50 (0.0059) | -0.02 (0.0035) | -2.73 (0.0368) | -1.35 (0.0227) |
Hybrid Empirical | -0.93 (0.0048) | -0.38 (0.0036) | -3.59 (0.0327) | -1.77 (0.0249) |
Hybrid Pareto 0.9 | -0.37 (0.0069) | -0.03 (0.0033) | -3.06 (0.0310) | -2.97 (0.0154) |
Hybrid Pareto 0.95 | -0.62 (0.0061) | -0.03 (0.0035) | -2.74 (0.0368) | -1.35 (0.0227) |
RMSE of cutoff | ||||
Empirical | 1.35 (0.0039) | 0.80 (0.0031) | 7.47 (0.0789) | 5.28 (0.0360) |
Normal | 1.82 (0.0024) | 1.72 (0.0014) | 7.01 (0.0180) | 6.14 (0.0090) |
Log Normal | 1.47 (0.0026) | 1.39 (0.0014) | 6.86 (0.0059) | 6.82 (0.0031) |
MAD | 2.69 (0.0010) | 2.68 (0.0005) | 9.08 (0.0013) | 9.09 (0.0006) |
Log MAD | 2.07 (0.0022) | 2.04 (0.0012) | 8.43 (0.0030) | 8.48 (0.0014) |
Pareto 0.9 | 1.28 (0.0059) | 0.65 (0.0029) | 6.88 (0.0619) | 4.28 (0.0133) |
Pareto 0.95 | 1.28 (0.0052) | 0.70 (0.0033) | 7.84 (0.0871) | 4.74 (0.0294) |
Hybrid Empirical | 1.34 (0.0037) | 0.80 (0.0031) | 7.45 (0.0790) | 5.28 (0.0360) |
Hybrid Pareto 0.9 | 1.43 (0.0057) | 0.66 (0.0030) | 6.91 (0.0616) | 4.28 (0.0133) |
Hybrid Pareto 0.95 | 1.37 (0.0050) | 0.71 (0.0033) | 7.85 (0.0870) | 4.74 (0.0294) |