Table 3. The evaluation performance of the pipeline for the simulated SNPs.
Random Forests (RF) Run | RF+Stepwise | RF+Ridge regression | RF+Lasso | |||
---|---|---|---|---|---|---|
#Iterations | Number of trees (ntree) | % Variance all (p) SNPs | % Variance k SNPs | Model significance (r-squared & p-values) | Model significance (%Variance) | Model significance (r-squared & p-values) |
1 | 500 | 1.14 | 11.84 | 0.12 & 7.342e-12 | 24.36 | 0.14 & 2.482e-13 |
2 | 1000 | 1.71 | 16.36 | 0.14 & 1.042e-13 | 27.51 | 0.20 & 2.2e-16 |
3 | 2000 | 2.55 | 21.31 | 0.15 & 1.082e-14 | 28.97 | 0.22 & 2.2e-16 |
4 | 3000 | 1.6 | 19.34 | 0.13 & 1.604e-12 | 28.2 | 0.19 & 2.2e-16 |