Skip to main content

Table 2 Median model sizes and the corresponding interquartile ranges (IQR) as well as the average true positives for phenotypes Q1 and Q2 for all investigated methods summarized across the 200 repetitions (first three columns)

From: A novel algorithm for simultaneous SNP selection in high-dimensional genome-wide association studies

 

Results

Comparisons

 

Method

Model size

TP

TP

TP

TP

  

Median (IQR)

Method

CAR

COR

RND

Q1

      
 

CAR

51 (53)

5.85

5.85

5.42

0.23

 

COR

176 (108)

8.06

8.99

8.06

0.88

 

NEG

1390 (118)

15.31

17.57

14.38

6.60

 

MCP

20 (5)

4.11

4.19

3.95

0.12

 

BOOST

53 (5)

5.84

5.91

5.50

0.25

 

LASSO

37 (31)

5.19

5.21

4.89

0.18

Q2

      
 

CAR

31 (38)

2.93

2.93

2.85

0.29

 

COR

1 (7)

0.38

0.21

0.38

0.00

 

NEG

1632 (755)

20.21

28.08

25.90

14.50

 

MCP

29 (5)

2.75

2.82

2.76

0.28

 

BOOST

59 (6)

3.92

4.34

3.82

0.59

 

LASSO

15 (36)

1.50

1.88

1.97

0.14

  1. For comparison, the last three columns show the average true positives at the specified model size for CAR, COR and RND. The best performing method is shown in bold, the second best in italic.