Table 7 P-values for pairwise comparisons based on the RMSE metric on the combined phenotypic and genotypic features over the test set.

From: Powdery mildew resistance prediction in Barley (Hordeum Vulgare L) with emphasis on machine learning approaches

 

RRF

RGP

RNET

RDT

MRF

MGP

MNET

MDT

FRF

FGP

FNET

FDT

RRF

1

0.235

0.738

0.001

1.000

0.747

0.997

0.002

1.000

0.415

0.485

0.002

RGP

0.235

1

0.000

0.899

0.046

1.000

0.013

0.913

0.029

1.000

 < 0.0001

0.910

RNET

0.738

0.000

1

 < 0.0001

0.979

0.008

0.999

 < 0.0001

0.992

0.001

1.000

 < 0.0001

RDT

0.001

0.899

 < 0.0001

1

 < 0.0001

0.410

 < 0.0001

1.000

 < 0.0001

0.743

 < 0.0001

1.000

MRF

1.000

0.046

0.979

 < 0.0001

1

0.313

1.000

0.000

1.000

0.107

0.885

 < 0.0001

MGP

0.747

1.000

0.008

0.410

0.313

1

0.133

0.434

0.235

1.000

0.002

0.429

MNET

0.997

0.013

0.999

 < 0.0001

1.000

0.133

1

 < 0.0001

1.000

0.035

0.982

 < 0.0001

MDT

0.002

0.913

 < 0.0001

1.000

0.000

0.434

 < 0.0001

1

 < 0.0001

0.765

 < 0.0001

1.000

FRF

1.000

0.029

0.992

 < 0.0001

1.000

0.235

1.000

 < 0.0001

1

0.072

0.936

 < 0.0001

FGP

0.415

1.000

0.001

0.743

0.107

1.000

0.035

0.765

0.072

1

0.000

0.761

FNET

0.485

 < 0.0001

1.000

 < 0.0001

0.885

0.002

0.982

 < 0.0001

0.936

0.000

1

 < 0.0001

FDT

0.002

0.910

 < 0.0001

1.000

 < 0.0001

0.429

 < 0.0001

1.000

 < 0.0001

0.761

 < 0.0001

1

  1. The compared models are RRF (RReliefF-RF), RGP (RReliefF-GP), RNET (RReliefF-NET), RDT (RReliefF-DT), MRF (MRMR-RF), MGP (MRMR-GP), MNET (MRMR-NET), MDT (MRMR-DT), FRF (FTest-RF), FGP (FTest-GP), FNET (FTest-NET), and FDT (FTest-DT).
  2. Significant values are given in bold.
Back to article page