plsRglm (version 0.3.3)

plsRglm: Partial least squares Regression generalized linear models

Description

This function implements Partial least squares Regression generalized linear models complete or incomplete datasets.

Usage

plsRglm(dataY, dataX, nt = 2, limQ2set = 0.0975, dataPredictY = dataX, modele = "pls", family = NULL, typeVC = "none", EstimXNA = FALSE, scaleX = TRUE, scaleY = NULL, pvals.expli = FALSE, alpha.pvals.expli = 0.05, MClassed = FALSE, tol_Xi = 10^(-12))

Arguments

dataY

response (training) dataset

dataX

predictor(s) (training) dataset

nt

number of components to be extracted

limQ2set

limit value for the Q2

dataPredictY

predictor(s) (testing) dataset

modele

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

family

for the present moment the family argumlent is ignored and set thanks to the value of modele.

typeVC

type of leave one out crossed validation. For back compatibility purpose. [object Object],[object Object],[object Object],[object Object]

EstimXNA

only for modele="pls". Set whether the missing X values have to be estimated.

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.

pvals.expli

should individual p-values be reported to tune model selection ?

alpha.pvals.expli

level of significance for predictors when pvals.expli=TRUE

MClassed

number of missclassed cases, should only be used for binary responses

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

• Depends on the model that was used to fit the model.

Details

There are four different models available : [object Object],[object Object],[object Object],[object Object]

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

See Also

plsR

Examples

data(Cornell)
XCornell<-Cornell[,1:7]
yCornell<-Cornell[,8]
plsRglm(yCornell,XCornell,3)$uscores
plsRglm(yCornell,XCornell,3)$pp
plsRglm(yCornell,XCornell,3)$Coeffs
plsRglm(yCornell,XCornell,10)$InfCrit
plsRglm(yCornell,XCornell,10,modele="pls-glm-gaussian")$InfCrit
rm(list=c("XCornell","yCornell"))

data(pine)
Xpine<-pine[,1:10]
ypine<-pine[,11]
plsRglm(log(ypine),Xpine,1)$Std.Coeffs
plsRglm(log(ypine),Xpine,1)$Coeffs
plsRglm(log(ypine),Xpine,4)$Std.Coeffs
plsRglm(log(ypine),Xpine,4)$Coeffs
plsRglm(log(ypine),Xpine,4)$PredictY[1,]
plsRglm(log(ypine),Xpine,4,dataPredictY=Xpine[1,])$PredictY[1,]

XpineNAX21 <- Xpine
XpineNAX21[1,2] <- NA
str(plsRglm(log(ypine),XpineNAX21,2))
plsRglm(log(ypine),XpineNAX21,4)$Std.Coeffs
plsRglm(log(ypine),XpineNAX21,4)$YChapeau[1,]
plsRglm(log(ypine),Xpine,4)$YChapeau[1,]
plsRglm(log(ypine),XpineNAX21,4)$CoeffC
plsRglm(log(ypine),XpineNAX21,4,EstimXNA=TRUE)$XChapeau
plsRglm(log(ypine),XpineNAX21,4,EstimXNA=TRUE)$XChapeauNA

# compare pls-glm-gaussian with classic plsR
cbind(plsRglm(log(ypine),Xpine,4,modele="pls")$Std.Coeffs,plsRglm(log(ypine),Xpine,4,modele="pls-glm-gaussian")$Std.Coeffs)

# without missing data
cbind(log(ypine),plsRglm(log(ypine),Xpine,4,modele="pls")$YChapeau,plsRglm(log(ypine),Xpine,4,modele="pls-glm-gaussian")$YChapeau)
cbind(log(ypine),plsRglm(log(ypine),XpineNAX21,4,modele="pls")$YChapeau,plsRglm(log(ypine),XpineNAX21,4,modele="pls-glm-gaussian")$YChapeau)

# with missing data
cbind((log(ypine)),plsRglm(log(ypine),XpineNAX21,4,modele="pls")$YChapeau,plsRglm(log(ypine),XpineNAX21,4,modele="pls-glm-gaussian")$YChapeau)
cbind((log(ypine)),plsRglm(log(ypine),XpineNAX21,4,modele="pls")$ValsPredictY,plsRglm(log(ypine),XpineNAX21,4,modele="pls-glm-gaussian")$ValsPredictY)
rm(list=c("Xpine","ypine"))

data(fowlkes)
Xfowlkes <- fowlkes[,2:13]
yfowlkes <- fowlkes[,1]
modpls <- plsRglm(yfowlkes,Xfowlkes,4,modele="pls-glm-logistic",pvals.expli=TRUE)
modpls$pvalstep
rm(list=c("Xfowlkes","yfowlkes","modpls"))

data(aze_compl)
Xaze_compl<-aze_compl[,2:34]
yaze_compl<-aze_compl$y
plsRglm(yaze_compl,Xaze_compl,nt=10,modele="pls",MClassed=TRUE)$InfCrit
modpls <- plsRglm(yaze_compl,Xaze_compl,nt=10,modele="pls-glm-logistic",MClassed=TRUE,pvals.expli=TRUE)
modpls$InfCrit
modpls$valpvalstep
modpls$Coeffsmodel_vals

plot(plsRglm(yaze_compl,Xaze_compl,4,modele="pls-glm-logistic")$FinalModel)
plsRglm(yaze_compl[-c(99,72)],Xaze_compl[-c(99,72),],4,modele="pls-glm-logistic",pvals.expli=TRUE)$pvalstep
plot(plsRglm(yaze_compl[-c(99,72)],Xaze_compl[-c(99,72),],4,modele="pls-glm-logistic",pvals.expli=TRUE)$FinalModel)
rm(list=c("Xaze_compl","yaze_compl","modpls"))


data(bordeaux)
Xbordeaux<-bordeaux[,1:4]
ybordeaux<-factor(bordeaux$Quality,ordered=TRUE)
modpls <- plsRglm(ybordeaux,Xbordeaux,10,modele="pls-glm-polr")
modpls$Coeffsmodel_vals
modpls$InfCrit

XbordeauxNA<-Xbordeaux
XbordeauxNA[1,1] <- NA
modplsNA <- plsRglm(ybordeaux,XbordeauxNA,10,modele="pls-glm-polr")
modplsNA$Coeffsmodel_vals
modplsNA$InfCrit
rm(list=c("Xbordeaux","XbordeauxNA","ybordeaux","modplsNA"))


#install.packages(chemometrics)
library(chemometrics)
data(hyptis)
yhyptis <- factor(hyptis$Group,ordered=TRUE)
Xhyptis <- as.data.frame(hyptis[,c(1:6)])
options(contrasts = c("contr.treatment", "contr.poly"))
modpls2 <- plsRglm(yhyptis,Xhyptis,6,modele="pls-glm-polr")
modpls2$Coeffsmodel_vals
modpls2$InfCrit
modpls2$Coeffs
modpls2$std.coeffs

table(yhyptis,predict(modpls2$FinalModel,type="class"))
rm(list=c("yhyptis","Xhyptis","modpls2"))


dimX <- 6
Astar <- 4
dataAstar4 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar4)[,1]
Xsimbin1 <- dicho(dataAstar4)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar4","ysimbin1","Xsimbin1","modplsglm"))


dimX <- 24
Astar <- 2
dataAstar2 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar2)[,1]
Xsimbin1 <- dicho(dataAstar2)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar2","ysimbin1","Xsimbin1","modplsglm"))


dimX <- 24
Astar <- 3
dataAstar3 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar3)[,1]
Xsimbin1 <- dicho(dataAstar3)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar3","ysimbin1","Xsimbin1","modplsglm"))


dimX <- 24
Astar <- 4
dataAstar4 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar4)[,1]
Xsimbin1 <- dicho(dataAstar4)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar4","ysimbin1","Xsimbin1","modplsglm"))


dimX <- 24
Astar <- 5
dataAstar5 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar5)[,1]
Xsimbin1 <- dicho(dataAstar5)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar5","ysimbin1","Xsimbin1","modplsglm"))


dimX <- 24
Astar <- 6
dataAstar6 <- t(replicate(250,simul_data_UniYX(dimX,Astar)))
ysimbin1 <- dicho(dataAstar6)[,1]
Xsimbin1 <- dicho(dataAstar6)[,2:(dimX+1)]
modplsglm <- plsRglm(ysimbin1,Xsimbin1,10,modele="pls-glm-logistic")
modplsglm$computed_nt
modplsglm$InfCrit
rm(list=c("dimX","Astar","dataAstar6","ysimbin1","Xsimbin1","modplsglm"))