Table 3.
Power of MDR (from Ritchie et al. 2007) to detect primary genetic model in data with genetic heterogeneity.
| Source of Noise | Power (%) to Detect Primary Model (5,10) | |||||
| Model 1 | Model 2 | Model 3 | Model 4 | Model 5 | Model 6 | |
| GH | 30 | 18 | 19 | 25 | 8 | 8 |
| GE+GH | 39 | 18 | 19 | 25 | 8 | 8 |
| GH+PC | 11 | 18 | 5 | 3 | 4 | 2 |
| GH+MS | 28 | 23 | 19 | 19 | 9 | 13 |
| GE+GH+PC | 10 | 18 | 8 | 4 | 3 | 3 |
| GE+GH+MS | 29 | 22 | 21 | 20 | 7 | 4 |
| GH+PC+MS | 12 | 22 | 5 | 5 | 2 | 4 |
| GE+GH+PC+MS | 16 | 17 | 4 | 3 | 1 | 3 |
GE = 5% Genotyping Error; GH = 50% Genetic Heterogeneity; PC = 50% Phenocopy; MS = 5% Missing Data