Table 3 The frequencies of the relevant variables obtained by the sparse logistic regressions with the L _1/2 , L _EN and L ₁ penalties in 30 runs

$\begin{array}{c}\hfill \rho =0.1,\hfill \\ \hfill \sigma =0.2\hfill \end{array}$

n=50

L_1/2

21

22

19

15

15

L_EN

24

25

21

17

17

L₁

22

24

20

15

17

n=80

L_1/2

30

30

30

30

30

L_EN

30

29

30

30

30

L₁

30

29

30

30

30

n=100

L_1/2

30

30

30

30

30

L_EN

30

30

30

30

30

L₁

30

30

30

30

30

$\begin{array}{c}\hfill \rho =0.1,\hfill \\ \hfill \sigma =0.6\hfill \end{array}$

n=50

L_1/2

17

17

17

14

14

L_EN

18

19

17

16

14

L₁

18

18

18

16

15

n=80

L_1/2

30

29

30

28

28

L_EN

30

28

30

28

27

L₁

30

28

30

27

26

n=100

L_1/2

30

30

30

30

30

L_EN

30

30

30

30

30

L₁

30

30

30

28

30

$\begin{array}{c}\hfill \rho =0.4,\hfill \\ \hfill \sigma =0.2\hfill \end{array}$

n=50

L_1/2

19

18

18

16

15

L_EN

21

22

21

17

17

L₁

18

21

19

16

17

n=80

L_1/2

30

30

30

30

30

L_EN

30

28

30

29

29

L₁

30

27

30

29

29

n=100

L_1/2

30

30

30

30

30

L_EN

30

30

30

30

30

L₁

30

30

30

29

29

$\begin{array}{c}\hfill \rho =0.4,\hfill \\ \hfill \sigma =0.6\hfill \end{array}$

n=50

L_1/2

14

16

15

12

12

L_EN

17

17

17

12

14

L₁

17

15

14

9

13

n=80

L_1/2

29

25

26

28

29

L_EN

28

24

24

27

24

L₁

27

24

24

23

23

n=100

L_1/2

30

29

30

30

30

L_EN

30

27

28

28

30

L₁

29

27

27

28

30