PLS_glm_kfoldcv: Partial least squares regression glm models with kfold cross validation

Description

This function implements kfold cross validation on complete or incomplete datasets for partial least squares regression generalized linear models

Usage

PLS_glm_kfoldcv(dataY, dataX, nt = 2, limQ2set = 0.0975, modele = "pls", family = NULL, K = nrow(dataX), NK = 1, grouplist = NULL, random = FALSE, scaleX = TRUE, scaleY = NULL, keepcoeffs = FALSE, keepfolds = FALSE, keepdataY = TRUE, keepMclassed=FALSE, tol_Xi = 10^(-12))

Arguments

dataY

response (training) dataset

dataX

predictor(s) (training) dataset

number of components to be extracted

limQ2set

limit value for the Q2

modele

name of the PLS glm model to be fitted ("pls", "pls-glm-gaussian", "pls-glm-logistic", "pls-glm-polr").

family

glm family. not used at the moment

number of groups

number of times the group division is made

grouplist

to specify the members of the K groups

random

should the K groups be made randomly

scaleX

scale the predictor(s) : must be set to TRUE for modele="pls" and should be for glms pls.

scaleY

scale the response : Yes/No. Ignored since non always possible for glm responses.

keepcoeffs

shall the coefficients for each model be returned

keepfolds

shall the groups' composition be returned

keepdataY

shall the observed value of the response for each one of the predicted value be returned

keepMclassed

shall the number of miss classed be returned (unavailable)

tol_Xi

minimal value for Norm2(Xi) and $\mathrm{det}(pp' \times pp)$ if there is any missing value in the dataX. It defaults to $10^{-12}$

Value

results_kfoldslist of NK. Each element of the list sums up the results for a group division: [object Object],[object Object],[object Object]
foldslist of NK. Each element of the list sums up the informations for a group division: [object Object],[object Object],[object Object]
dataY_kfoldslist of NK. Each element of the list sums up the results for a group division: [object Object],[object Object],[object Object]
callthe call of the function

Details

Predicts 1 group with the K-1 other groups. Leave one out cross validation is thus obtained for K==nrow(dataX).

References

Nicolas Meyer, Myriam Maumy-Bertrand et Fr�d�ric{Fr'ed'eric} Bertrand (2010). Comparaison de la r�gression{r'egression} PLS et de la r�gression{r'egression} logistique PLS : application aux donn�es{donn'ees} d'all�lotypage{d'all'elotypage}. Journal de la Soci�t� Fran�aise de Statistique, 151(2), pages 1-18. http://smf4.emath.fr/Publications/JSFdS/151_2/pdf/sfds_jsfds_151_2_1-18.pdf

Examples

Run this code

data(Cornell)
XCornell<-Cornell[,1:7]
yCornell<-Cornell[,8]
bbb <- PLS_glm_kfoldcv(dataY=yCornell,dataX=XCornell,nt=10,NK=1,modele="pls")
kfolds2CVinfos_glm(bbb)

PLS_glm_kfoldcv(dataY=yCornell,dataX=XCornell,nt=3,modele="pls-glm-gaussian",K=12)
PLS_glm_kfoldcv(dataY=yCornell,dataX=XCornell,nt=3,modele="pls-glm-gaussian",K=6,NK=2,random=TRUE,keepfolds=TRUE)$results_kfolds
PLS_glm_kfoldcv(dataY=yCornell,dataX=XCornell,nt=3,modele="pls-glm-gaussian",K=6,NK=2,random=FALSE,keepfolds=TRUE)$results_kfolds

bbb2 <- PLS_glm_kfoldcv(dataY=yCornell,dataX=XCornell,nt=10,modele="pls-glm-gaussian",keepcoeffs=TRUE)

#For Jackknife computations
kfolds2coeff(bbb2)
boxplot(kfolds2coeff(bbb2)[,1])

kfolds2Chisqind(bbb2)
kfolds2Chisq(bbb2)
kfolds2CVinfos_glm(bbb2)
PLS_v1(log(yCornell),XCornell,10,typeVC="standard")$CVinfos
rm(list=c("XCornell","yCornell","bbb","bbb2"))


data(pine)
Xpine<-pine[,1:10]
ypine<-pine[,11]
bbb <- PLS_glm_kfoldcv(dataY=ypine,dataX=Xpine,nt=10,modele="pls-glm-gaussian",K=10,keepcoeffs=TRUE,keepfolds=FALSE)

#For Jackknife computations
kfolds2coeff(bbb)
boxplot(kfolds2coeff(bbb)[,1])

kfolds2Chisqind(bbb)
kfolds2Chisq(bbb)
kfolds2CVinfos_glm(bbb)
PLS_v1(log(ypine),Xpine,10,typeVC="standard")$CVinfos

XpineNAX21 <- Xpine
XpineNAX21[1,2] <- NA

bbb2 <- PLS_glm_kfoldcv(dataY=ypine,dataX=XpineNAX21,nt=10,modele="pls-glm-gaussian",K=10,keepcoeffs=TRUE,keepfolds=FALSE)

#For Jackknife computations
kfolds2coeff(bbb2)
boxplot(kfolds2coeff(bbb2)[,1])

kfolds2Chisqind(bbb2)
kfolds2Chisq(bbb2)
kfolds2CVinfos_glm(bbb2)
PLS_v1(log(ypine),XpineNAX21,10,typeVC="standard")$CVinfos
rm(list=c("Xpine","XpineNAX21","ypine","bbb","bbb2"))


data(aze_compl)
Xaze_compl<-aze_compl[,2:34]
yaze_compl<-aze_compl$y
bbb <- PLS_glm_kfoldcv(yaze_compl,Xaze_compl,nt=10,K=10,modele="pls")
kfolds2coeff(bbb)
bbb2 <- PLS_glm_kfoldcv(yaze_compl,Xaze_compl,nt=10,K=10,modele="pls-glm-logistic")
kfolds2CVinfos_v2(bbb,MClassed=TRUE)
kfolds2CVinfos_v2(bbb2,MClassed=TRUE)
kfolds2coeff(bbb2)

kfolds2Chisqind(bbb2)
kfolds2Chisq(bbb2)
kfolds2CVinfos_glm(bbb2)
rm(list=c("Xaze_compl","yaze_compl","bbb","bbb2"))

Run the code above in your browser using DataLab