a) MAS
 
Inferior


 
WAD

AD

FC

RP

modT

samT

shrinkT

ibmT


Superior

WAD



2.1E07

6.7E07

2.3E06

2.2E02

1.7E02

2.0E02

1.8E01


AD

1.0E+00



8.1E01

2.9E04

1.0E+00

1.0E+00

1.0E+00

1.0E+00


FC

1.0E+00

1.9E01



2.6E04

1.0E+00

1.0E+00

1.0E+00

1.0E+00


RP

1.0E+00

1.0E+00

1.0E+00



1.0E+00

1.0E+00

1.0E+00

1.0E+00


modT

9.8E01

8.6E04

4.0E03

1.4E04



4.7E01

9.0E01

1.0E+00


samT

9.8E01

2.5E04

2.0E03

6.6E05

5.3E01



6.9E01

1.0E+00


shrinkT

9.8E01

4.0E04

2.2E03

9.0E05

1.0E01

3.1E01



1.0E+00


ibmT

8.2E01

4.7E05

2.6E04

2.6E05

2.2E04

2.3E03

2.9E04



(b) RMA
 
Inferior

 
WAD

AD

FC

RP

modT

samT

shrinkT

ibmT

Superior

WAD



9.8E01

9.8E01

8.9E01

3.0E01

3.1E01

2.5E01

4.4E01


AD

2.3E02



4.7E01

8.3E02

9.2E03

1.1E02

7.2E03

2.8E02


FC

2.4E02

5.3E01



8.8E02

1.1E02

1.3E02

8.4E03

3.1E02


RP

1.1E01

9.2E01

9.1E01



8.4E02

9.7E02

6.6E02

1.7E01


modT

7.0E01

9.9E01

9.9E01

9.2E01



5.6E01

6.5E02

1.0E+00


samT

6.9E01

9.9E01

9.9E01

9.0E01

4.4E01



2.1E01

8.3E01


shrinkT

7.5E01

9.9E01

9.9E01

9.3E01

9.4E01

7.9E01



1.0E+00


ibmT

5.6E01

9.7E01

9.7E01

8.3E01

3.2E03

1.7E01

1.9E03



(c) DFW
 
Inferior

 
WAD

AD

FC

RP

modT

samT

shrinkT

ibmT

Superior

WAD



1.0E+00

1.0E+00

1.0E+00

1.3E01

1.2E01

4.5E01

1.6E01


AD

2.5E03



1.6E01

9.6E01

5.1E02

4.7E02

2.1E01

6.9E02


FC

2.6E03

8.4E01



9.6E01

5.1E02

4.7E02

2.1E01

6.9E02


RP

8.7E04

4.2E02

4.1E02



3.0E02

3.0E02

1.1E01

4.4E02


modT

8.7E01

9.5E01

9.5E01

9.7E01



8.6E02

9.9E01

8.5E01


samT

8.8E01

9.5E01

9.5E01

9.7E01

9.1E01



9.9E01

1.0E+00


shrinkT

5.5E01

7.9E01

7.9E01

8.9E01

6.1E03

1.0E02



2.6E02


ibmT

8.4E01

9.3E01

9.3E01

9.6E01

1.5E01

5.2E04

9.7E01



 The pvalues between the 36 AUC values from a possibly superior method and those from a possibly inferior method were calculated by a onetail paired ttest. The null hypothesis is that the mean of the 36 AUC values for one method is the same as that for the other method. There are two pvalues for two methods compared. For example, in (a) MASpreprocessed data, the pvalue is 1.8E01 when the alternative hypothesis is that the mean of the 36 AUC values for WAD is greater than that for ibmT while the pvalue is 8.2E01 when the alternative hypothesis is that the mean of the 36 AUC values for ibmT is greater than that for WAD. Combinations having p < 0.05 are highlighted in bold.