Skip to main content

Table 5 Analysis of variance of F score, precision and sensitivity by balancing method and feature selection for HBV

From: Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines

Precision source

SS

df

MS

F

p

 Method

0.0004

2

0.0002

13.088

0.000 (a)

 Pre-processing

0.0013

1

0.0013

80.504

0.000 (a)

 Method.Pre-processing

0.0004

2

0.0002

12.222

0.000 (a)

Sensitivity Source

SS

df

MS

F

p

 Method

1.6151

2

0.8075

159.98

0.000 (a)

 Pre-processing

1.9877

1

1.9877

393.78

0.000 (a)

 Method.Pre-processing

2.8062

2

1.4031

277.97

0.000 (a)

F score Source

SS

df

MS

F

p

 Method

0.0011

2

0.0006

10.838

0.000 (a)

 Pre-processing

0.0025

1

0.0025

47.154

0.000 (a)

 Method.Pre-processing

0.0003

2

0.0002

3.007

0.052

  1. (a) = Significant at 0.0025 level with adjustment for multiple testing. Method = simple downsizing, multiple downsizing or SMOTE. Pre-processing = random forest variable selection or not. Method.Pre-processing = the interaction between Pre-processing and Method
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us