Skip to main content

Table 2 Misclassification rate - case 2

From: Comparison of classification methods that combine clinical data and high-dimensional mass spectrometry data

 

μ =2

 

n=100

n=200

n=500

1) Clin

43 (10)

43 (6)

44 (4)

2) Boost

41 (13)

28 (6)

15 (3)

3) BoostOffClin

39 (13)

30 (6)

13 (3)

4) ClinOffBoost

40 (14)

28 (7)

14 (3)

5) SGPLS

41 (11)

32 (8)

14 (3)

6) SGPLSOffClin

41 (10)

36 (8)

14 (4)

7) ClinOffSGPLS

40 (12)

32 (8)

15 (4)

8) RPLS

40 (11)

34 (7)

29 (4)

9) RPLSOffClin

38 (11)

36 (9)

30 (4)

10) ClinOffRPLS

38 (14)

34 (7)

29 (4)

Oracle

15 (8)

8 (4)

6 (2)

  1. This table contains the mean and the standard deviation of the MCR over 50 simulated datasets for each compared method and for μ=2 (i.e. higher predictive importance of MS data than clinical data).
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us