plsRglm (version 0.3.3)

kfolds2coeff: Extracts coefficients from kfold cross validated partial least squares regression models

Description

This fonction extracts coefficients from kfold cross validated partial least squares regression models

Usage

kfolds2coeff(pls_kfolds)

Arguments

pls_kfolds

an object that is a kfold cross validated partial least squares regression models either lm or glm

Value

• coef.all
  matrix with the values of the coefficients for each leave one out step or NULL if another type of cross validation was used.

Details

This fonctions works for "lm" or "glm" plsR models.

References

~put references to the literature/web site here ~

See Also

kfolds2Pressind, kfolds2Press, kfolds2Mclassedind, kfolds2Mclassed and kfolds2CVinfos_lm to extract and transform results from kfold cross validation.

Examples

data(Cornell)
XCornell<-Cornell[,1:7]
yCornell<-Cornell[,8]
data(aze_compl)
Xaze_compl<-aze_compl[,2:34]
yaze_compl<-aze_compl$y
data(pine)
Xpine<-pine[,1:10]
ypine<-pine[,11]
bbb <- PLS_v1_kfoldcv(dataY=yCornell,dataX=XCornell,nt=3,keepcoeffs=TRUE)
bbb2 <- PLS_v1_kfoldcv(dataY=log(ypine),dataX=Xpine,nt=4,keepcoeffs=TRUE)
kfolds2coeff(bbb)
boxplot(kfolds2coeff(bbb)[,1])
kfolds2coeff(bbb2)
boxplot(kfolds2coeff(bbb2)[,2])
rm(list=c("XCornell","yCornell","Xpine","ypine","bbb","bbb2"))