Skip to main content

Table 2 Specificity, sensitivity, phi correlation and misclassification rate for each model at detecting different α and (1-α) percentiles of extreme animals in the testing set within line A

From: Genome-wide prediction of discrete traits using bayesian regressions and machine learning

Parameter Method α (number of records)
   0.05 (12) 0.10 (79) 0.25 (98) 0.50 (138)
Specificity1 TBA 1 0.71 0.58 0.56
  BTL 1 0.94 0.75 0.74
  RF 1 0.88 0.78 0.79
  L2B 0.75 0.71 0.64 0.65
  LhB 0.75 0.71 0.61 0.67
Sensitivity1 TBA 0.75 0.58 0.58 0.56
  BTL 0.75 0.53 0.53 0.47
  RF 1 0.52 0.52 0.46
  L2B 0.75 0.48 0.48 0.51
  LhB 0.50 0.45 0.45 0.42
Phi correlation1 TBA 0.71 0.24 0.16 0.13
  BTL 0.71 0.39 0.27 0.22
  RF 1 0.33 0.29 0.26
  L2B 0.48 0.16 0.12 0.17
  LhB 0.24 0.13 0.06 0.09
Misclassification rate (%)2 TBA 17 39 42 43
  BTL 17 38 39 40
  RF 0 41 39 38
  L2B 25 47 46 42
  LhB 42 49 49 46
  1. 1Higher value is desirable; the best value for each percentile is in bold face;
  2. 2Lower value is desirable; the best value for each percentile is in bold face;
  3. TBA = Threshold Bayes A, BTL = Bayesian Threshold LASSO, RF = Random Forest; L2B = L2-boosting algorithm, LhB = Lh-boosting algorithm