Supervised principal components software for R

Authors: Eric Bair and Rob Tibshirani
Maintainer: Rob Tibshirani

This software, written in the R language, does prediction for a censored survival outcome, or a regression outcome, using the "supervised principal component" approach. It is especially useful when the number of features p is >> n, the number of samples, for example in microarray studies.

Based on the papers
Semi-supervised methods for predicting patient survival from gene expression papers (Bair, Tibshirani) PLOS
Prediction by supervised principal components (Bair, Hastie, Paul, Tibshirani) Stanford tech report

mpeg movie illustrating supervised principal components . [Can be viewed with any mpeg viewer: Quicktime is best, as it allows you to run the movie in manual steps.]
description of the movie

  • Superpc R package (Linux gz file)
    Superpc R package (Windows zip file)
    Superpc R package (MAC OS X tgz file)

  • Lymphoma data used in PLOS paper

  • Tutorial