Table 2 Model performance with Simulation Data and Different Parameter Values
From: Kernel based methods for accelerated failure time model with ultra-high dimensional data
|w i |s(λ*, p*) | Av. # of Vars | Exactly-match | Overfitting | Underfitting |
|---|---|---|---|---|
1 (0.01, 0.6) | 12.61 | 75% | 21% | 4% |
0.2 (0.002, 0.6) | 11.52 | 54% | 3% | 43% |
0.1 (0.001, 0.6) | 11.43 | 52% | 2% | 46% |