Skip to main content

Table 1

From: A comparison of random forests, boosting and support vector machines for genomic selection

CV/TBV Sample size Random Forests Boosting Support Vector Machines Ridge Regression BLUP
  Mean Range Mean Range Mean Range Mean Range Mean Range
CV 439 416-514 0.466 0.392-0.534 0.503 0.431-0.567 0.503 0.432-0.567 0.530 0.451-0.620
TBV 900   0.483   0.547   0.497   0.607  
  1. Predictive accuracies of random forests, boosted regression trees, epsilon support vector machines and RR-BLUP, expressed as the Pearson correlation between GEBVs and observed values from the 5-fold cross-validation (CV) and between GEBVs and TBV for non-phenotyped individuals (TBV).