superpc.train {superpc}R Documentation

Prediction by supervised principal components

Description

Does prediction of a quantitative regression or survival outcome, by the supervised principal components method.

Usage

superpc.train(data, type = c("survival", "regression"))

Arguments

data Data object with components x- p by n matrix of features, one observation per column; y- n-vector of outcome measurements; status- n-vector of censoring status (1= died or event occurred, 0=survived, or event was censored), needed for a censored survival outcome
type Problem type: "survival" for censored survival outcome, or "regression" for simple quantitative outcome

Details

Compute wald scores for each feature (gene), for later use in superpc.predict and superpc.cv

Value

gene.scores=gene.scores, type=type, call = this.call

feature.scores Score for each feature (gene)
type problem type
call calling sequence

Author(s)

Eric Bair and Robert Tibshirani

References

Bair E, Tibshirani R (2004) Semi-supervised methods to predict patient survival from gene expression data. PLoS Biol 2004 April; 2 (4): e108; http://www-stat.stanford.edu/~tibs/superpc

Examples

#generate some example data
set.seed(332)
x<-matrix(rnorm(1000*40),ncol=40)
y<-10+svd(x[1:60,])$v[,1]+ .1*rnorm(40)
status<- sample(c(rep(1,30),rep(0,10)))

featurenames <- paste("feature",as.character(1:1000),sep="")
data<-list(x=x,y=y, status=status, featurenames=featurenames)

a<- superpc.train(data, type="survival")

[Package Contents]