plsRcox (version 1.7.7)

predict.plsRcoxmodel: Print method for plsRcox models

Description

This function provides a predict method for the class "plsRcoxmodel"

Usage

# S3 method for plsRcoxmodel
predict(
  object,
  newdata,
  comps = object$computed_nt,
  type = c("lp", "risk", "expected", "terms", "scores"),
  se.fit = FALSE,
  weights,
  methodNA = "adaptative",
  verbose = TRUE,
  ...
)

Value

When type is "response", a matrix of predicted response values is returned.
When type is "scores", a score matrix is returned.

Arguments

object

An object of the class "plsRcoxmodel".

newdata

An optional data frame in which to look for variables with which to predict. If omitted, the fitted values are used.

comps

A value with a single value of component to use for prediction.

type

Type of predicted value. Choices are the linear predictor ("lp"), the risk score exp(lp) ("risk"), the expected number of events given the covariates and follow-up time ("expected"), the terms of the linear predictor ("terms") or the scores ("scores").

se.fit

If TRUE, pointwise standard errors are produced for the predictions using the Cox model.

weights

Vector of case weights. If weights is a vector of integers, then the estimated coefficients are equivalent to estimating the model from data with the individual cases replicated as many times as indicated by weights.

methodNA

Selects the way of predicting the response or the scores of the new data. For complete rows, without any missing value, there are two different ways of computing the prediction. As a consequence, for mixed datasets, with complete and incomplete rows, there are two ways of computing prediction : either predicts any row as if there were missing values in it (missingdata) or selects the prediction method accordingly to the completeness of the row (adaptative).

verbose

Should some details be displayed ?

...

Arguments to be passed on to survival::coxph and to plsRglm::PLS_lm.

Author

Frédéric Bertrand

http://www-irma.u-strasbg.fr/~fbertran/

References

plsRcox, Cox-Models in a high dimensional setting in R, Frederic Bertrand, Philippe Bastien, Nicolas Meyer and Myriam Maumy-Bertrand (2014). Proceedings of User2014!, Los Angeles, page 152.

Deviance residuals-based sparse PLS and sparse kernel PLS regression for censored data, Philippe Bastien, Frederic Bertrand, Nicolas Meyer and Myriam Maumy-Bertrand (2015), Bioinformatics, 31(3):397-404, doi:10.1093/bioinformatics/btu660.

See Also

predict.coxph

Examples

data(micro.censure)
data(Xmicro.censure_compl_imp)

X_train_micro <- apply((as.matrix(Xmicro.censure_compl_imp)),FUN="as.numeric",MARGIN=2)[1:80,]
Y_train_micro <- micro.censure$survyear[1:80]
C_train_micro <- micro.censure$DC[1:80]

modpls <- plsRcox(X_train_micro,time=Y_train_micro,event=C_train_micro,nt=3)

predict(modpls)    
#Identical to predict(modpls,type="lp")    

predict(modpls,type="risk")    
predict(modpls,type="expected")    
predict(modpls,type="terms")    
predict(modpls,type="scores")    

predict(modpls,se.fit=TRUE)    
#Identical to predict(modpls,type="lp")    
predict(modpls,type="risk",se.fit=TRUE)    
predict(modpls,type="expected",se.fit=TRUE)    
predict(modpls,type="terms",se.fit=TRUE)    
predict(modpls,type="scores",se.fit=TRUE)    


#Identical to predict(modpls,type="lp")    
predict(modpls,newdata=X_train_micro[1:5,],type="risk")    
#predict(modpls,newdata=X_train_micro[1:5,],type="expected")    
predict(modpls,newdata=X_train_micro[1:5,],type="terms")    
predict(modpls,newdata=X_train_micro[1:5,],type="scores")    

#Identical to predict(modpls,type="lp")    
predict(modpls,newdata=X_train_micro[1:5,],type="risk",se.fit=TRUE)    
#predict(modpls,newdata=X_train_micro[1:5,],type="expected",se.fit=TRUE)    
predict(modpls,newdata=X_train_micro[1:5,],type="terms",se.fit=TRUE)    
predict(modpls,newdata=X_train_micro[1:5,],type="scores")    

predict(modpls,newdata=X_train_micro[1:5,],type="risk",comps=1)    
predict(modpls,newdata=X_train_micro[1:5,],type="risk",comps=2)    
predict(modpls,newdata=X_train_micro[1:5,],type="risk",comps=3)    
try(predict(modpls,newdata=X_train_micro[1:5,],type="risk",comps=4))

predict(modpls,newdata=X_train_micro[1:5,],type="terms",comps=1)    
predict(modpls,newdata=X_train_micro[1:5,],type="terms",comps=2)    
predict(modpls,newdata=X_train_micro[1:5,],type="terms",comps=3)    
try(predict(modpls,newdata=X_train_micro[1:5,],type="terms",comps=4))

predict(modpls,newdata=X_train_micro[1:5,],type="scores",comps=1)    
predict(modpls,newdata=X_train_micro[1:5,],type="scores",comps=2)    
predict(modpls,newdata=X_train_micro[1:5,],type="scores",comps=3)    
try(predict(modpls,newdata=X_train_micro[1:5,],type="scores",comps=4))