OPLS-DA permutation test
1
0
Entering edit mode
Eddie • 0
@f2dcf917
Last seen 19 months ago
Belgium

Hi all, I run an OPLS-DA and worked fine. The problem I have is that the output of permuted model is identical to the original model and shows the the predictive component significant. I didn't understand how the permuted model performs identically to the original model and at the same time the pQ2Y=0.002. The score plot is also identical. Thank you

dataMatrixEF<-EFFECT.data[,-c(229:230)]
EF_oplsda <- opls(dataMatrixEF, Y_EF, predI = 1, scale="standard", orthoI = NA, subset=c(1:100))
               R2X(cum) R2Y(cum) Q2(cum) RMSEE RMSEP pre ort
Total             0.68         0.813         0.57      0.224    0.318   1   5
Warning message:
'permI' set to 0 because train/test partition is selected

EFperm<-dataMatrixEF[c(1:100),]
EFperm_oplsda <- opls(EFperm, perm_Y_EF, scaleC="standard",predI = 1, orthoI = NA,permI=500)

          R2X(cum) R2Y(cum) Q2(cum) RMSEE pre ort  pR2Y   pQ2
Total     0.68            0.813          0.57      0.224   1   5     0.002 0.002
Metabolomics • 1.2k views
ADD COMMENT
0
Entering edit mode
@etiennethevenot-8285
Last seen 14 months ago
France

Hi, If the permutated response is identical to the intial vector, the corresponding model is identical. This is why the similarity between the permutated and original response is plotted in abscissa in the "permutation" plot assessing the significance of the modeling.

ADD COMMENT

Login before adding your answer.

Traffic: 699 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6