Table 3.
Inference of the ROC curve by the semiparametric least squares based method (OLS), the ROC-GLM method (GLM) and the placement value method (PV). Cases and controls are drawn from normal distributions. (α0,α1) = (1.2, 0.45), (nD, nD̄) = (100, 100). Relative bias and sampling standard error from 500 simulations are shown. Relative bias = bias/true value × 100%.
| Parameter | True value | OLS | GLM | PV |
|---|---|---|---|---|
| (a,b) = (0.0001, 0.9999) | ||||
| α0 | 1.2 | 1.09(0.150) | 1.46(0.152) | 2.40(0.161) |
| α1 | 0.45 | 2.42(0.083) | 1.38(0.080) | 9.44(0.101) |
| R(0.2) | 0.794 | −0.14(0.040) | 0.16(0.038) | −0.53(0.040) |
| R(0.4) | 0.861 | −0.02(0.031) | 0.12(0.031) | 0.15(0.032) |
| R(0.7) | 0.924 | −0.02(0.023) | −0.002(0.023) | 0.38(0.024) |
| (a,b) = (0.0001,0.2) | ||||
| α0 | 1.2 | 0.18(0.246) | −1.79(0.235) | 7.45(0.266) |
| α1 | 0.45 | −0.62(0.141) | −6.82(0.130) | 14.04(0.159) |
| R(0.05) | 0.677 | 0.11(0.051) | 1.27(0.049) | −1.00(0.051) |
| R(0.1) | 0.733 | −0.02(0.046) | 0.51(0.046) | 0.11(0.045) |
| R(0.15) | 0.768 | −0.13(0.046) | 0.08(0.045) | 0.61(0.045) |