BCBCSF: Bias-Corrected Bayesian Classification with Selected Features

Fully Bayesian Classification with a subset of high-dimensional features, such as expression levels of genes. The data are modeled with a hierarchical Bayesian models using heavy-tailed t distributions as priors. When a large number of features are available, one may like to select only a subset of features to use, typically those features strongly correlated with the response in training cases. Such a feature selection procedure is however invalid since the relationship between the response and the features has be exaggerated by feature selection. This package provides a way to avoid this bias and yield better-calibrated predictions for future cases when one uses F-statistic to select features.

AuthorLonghai Li <longhai@math.usask.ca>
Date of publication2015-09-26 01:05:27
MaintainerLonghai Li <longhai@math.usask.ca>
LicenseGPL (>= 2)
Version1.0-1
http://www.r-project.org
http://math.usask.ca/~longhai

View on CRAN

Files in this package

BCBCSF
BCBCSF/src
BCBCSF/src/ccodes
BCBCSF/src/ccodes/adjfactor.c
BCBCSF/src/ccodes/pred.c
BCBCSF/src/all.c
BCBCSF/NAMESPACE
BCBCSF/data
BCBCSF/data/lymphoma.RData
BCBCSF/R
BCBCSF/R/tr-pr.r
BCBCSF/R/comp_pred.r
BCBCSF/MD5
BCBCSF/DESCRIPTION
BCBCSF/man
BCBCSF/man/evalpred.Rd BCBCSF/man/analyzefit.Rd BCBCSF/man/internal.Rd BCBCSF/man/data.Rd BCBCSF/man/example.Rd BCBCSF/man/fitpred.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.