sda-package {sda}R Documentation

The sda package

Description

This package performs linear and diagonal discriminant analysis with variable selection.

The classifier is trained using James-Stein-type shrinkage estimators. Variable selection is based on a univariate test statistics (multi-class cat score) and subsequent false non-discovery rate (FNDR) testing. In addition, higher criticism (HC) feature scores are computed and can also be used for feature thresholding.

This approach is particularly suited for high-dimensional classification. For details see Ahdesm"aki and Strimmer (2009).

Typically the functions in this package are applied in three steps:

The accompanying web site (see below) provides example R scripts to illustrate the functionality of this package.

Author(s)

Miika Ahdesm"aki and Korbinian Strimmer (http://strimmerlab.org/)

References

See website: http://strimmerlab.org/software/sda/

See Also

sda.ranking, sda, predict.sda.


[Package sda version 1.1.0 Index]