
Computes PRESS for k-fold cross validated partial least squares regression models.
Source:R/kfolds2Press.R
kfolds2Press.Rd
This function computes PRESS for k-fold cross validated partial least squares regression models.
Value
- list
Press vs number of components for the first group partition
- list()
...
- list
Press vs number of components for the last group partition
Note
Use cv.plsR
to create k-fold cross validated partial
least squares regression models.
References
Nicolas Meyer, Myriam Maumy-Bertrand et Frédéric Bertrand (2010). Comparing the linear and the logistic PLS regression with qualitative predictors: application to allelotyping data. Journal de la Societe Francaise de Statistique, 151(2), pages 1-18. https://www.numdam.org/item/JSFS_2010__151_2_1_0/
See also
kfolds2coeff
, kfolds2Pressind
,
kfolds2Mclassedind
and kfolds2Mclassed
to
extract and transforms results from k-fold cross validation.
Author
Frédéric Bertrand
frederic.bertrand@lecnam.net
https://fbertran.github.io/homepage/
Examples
data(Cornell)
XCornell<-Cornell[,1:7]
yCornell<-Cornell[,8]
kfolds2Press(cv.plsR(object=yCornell,dataX=data.frame(scale(as.matrix(XCornell))[,]),
nt=6,K=12,NK=1,verbose=FALSE))
#> [[1]]
#> [1] 55.70774 41.43274 20.27397 21.24240 24.51801
#>
kfolds2Press(cv.plsR(object=yCornell,dataX=data.frame(scale(as.matrix(XCornell))[,]),
nt=6,K=6,NK=1,verbose=FALSE))
#> [[1]]
#> [1] 60.67384 37.44834 17.35983 25.14694 26.97979
#>
rm(list=c("XCornell","yCornell"))
# \donttest{
data(pine)
Xpine<-pine[,1:10]
ypine<-pine[,11]
kfolds2Press(cv.plsR(object=ypine,dataX=Xpine,nt=10,NK=1,verbose=FALSE))
#> [[1]]
#> [1] 13.11383 16.07115 16.80484 16.01002 15.72696 16.01078 16.72261 16.89642
#> [9] 16.85360 17.47502
#>
kfolds2Press(cv.plsR(object=ypine,dataX=Xpine,nt=10,NK=2,verbose=FALSE))
#> [[1]]
#> [1] 14.34299 13.86224 14.29954 13.07896 13.11752 13.26533 14.52682 15.94571
#> [9] 16.40371 16.99492
#>
#> [[2]]
#> [1] 15.67525 15.99173 18.33649 17.94999 16.68851 15.81142 16.55737 17.36604
#> [9] 18.05244 18.14532
#>
XpineNAX21 <- Xpine
XpineNAX21[1,2] <- NA
kfolds2Press(cv.plsR(object=ypine,dataX=XpineNAX21,nt=10,NK=1,verbose=FALSE))
#> [[1]]
#> [1] 14.27440 14.75048 16.91953 15.77344 16.32399 16.01672 18.12347 21.36587
#> [9] 19.93249
#>
kfolds2Press(cv.plsR(object=ypine,dataX=XpineNAX21,nt=10,NK=2,verbose=FALSE))
#> [[1]]
#> [1] 15.98650 15.70826 14.85051 13.35485 21.30392 29.71824 21.93329 18.27147
#> [9] 18.92796
#>
#> [[2]]
#> [1] 14.58396 15.69717 25.24154 14.46923 21.63037 12.84356 12.93730 28.12907
#> [9] 19.54269
#>
rm(list=c("Xpine","XpineNAX21","ypine"))
# }