From: Screening the genome to detect an association with hypertension
ModelA | Number of End-nodes | Cohort 1 Observed Error | Cohort 1 Cross-validation | Cohort 1 Model applied to Cohort 2 |
---|---|---|---|---|
1) No Splits | 1 | 6.4% | 6.4% | 7.9% |
2) All M & E | 3 | 5.5% | 6.6% | 10.1% |
3) All M | 3 | 5.5% | 6.6% | 10.1% |
4) All E, subset of M | 3 | 5.5% | 6.6% | 10.1% |
5) All E, handpicked M | 1 | 6.4% | 6.4% | 7.9% |