This software is used to predict the discrete response based on selected high dimensional features, such as gene expression data. The data are modeled with Bayesian Gaussian models. 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 will appear stronger. This package provides a way to avoid this bias and yields well-calibrated prediction for the test cases when one uses F-statistic to select features.
R (>= 2.8.1)