Skip to main content

Table 3 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 B

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

Parameter

Method

α (number of records)

  

0.05 (7)

0.10 (25)

0.25 (78)

0.50 (137)

Specificity1

TBA

0.75

0.86

0.74

0.75

 

BTL

0.75

0.86

0.61

0.58

 

RF

0.75

0.57

0.48

0.37

 

L2B

1

0.71

0.57

0.48

 

LhB

0.75

0.71

0.57

0.63

Sensitivity1

TBA

1

0.95

0.64

0.58

 

BTL

1

1

0.75

0.75

 

RF

1

1

0.95

0.94

 

L2B

1

0.72

0.56

0.64

 

LhB

0.67

0.78

0.73

0.69

Phi correlation1

TBA

0.75

0.80

0.34

0.34

 

BTL

0.75

0.90

0.34

0.32

 

RF

0.75

0.70

0.50

0.38

 

L2B

1

0.40

0.12

0.12

 

LhB

0.42

0.46

0.28

0.32

Misclassification rate (%)2

TBA

14

8

35

34

 

BTL

14

4

29

32

 

RF

14

12

19

31

 

L2B

0

28

44

43

 

LhB

29

24

32

36

  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