Table 3.
Mean bias (i.e. MSE) based on simulation results comparing the conventional maximum likelihood method (Wald) and the PML method
| All outcome phenotypes |
Excluding complete separation |
|||||
|---|---|---|---|---|---|---|
| Wald | PML | # phenotypesa | Wald | PML | # phenotypesa | |
| Null hypothesis (Type I error) | ||||||
| OR = 1 | 170.1 | 1.4 | 720 | 0.85 | 0.76 | 526 |
| Alternative hypothesis (Power) | ||||||
| OR = 2 | 15.3 | 0.4 | 11 | 0.21 | 0.18 | 10 |
| OR = 3 | 10.2 | 0.3 | 11 | 0.19 | 0.16 | 11 |
Note: Logistic regressions performed with PS adjustment, using PS generated with elastic-net penalty of α = 0.1.
a
Average number of outcome phenotypes remaining in the simulated datasets.