plsdof-package {plsdof}R Documentation

Degrees of Freedom and Confidence Intervals for Partial Least Squares Regression

Description

The plsdof package provides Degrees of Freedom estimates for Kernel Partial Least Squares Regression and its kernel extension. The package also provides model selection based on various information criteria (aic, bic, gmdl) and based on cross-validation. For linear Partial Least Squares, the package computes the approximate distribution of the regression coefficients. This allows the construction of confidence intervals and tests.

Details

Package: plsdof
Type: Package
Version: 0.1-1
Date: 2009-11-27
License: GPL (>=2)
LazyLoad: yes

Author(s)

Nicole Kraemer, Mikio L. Braun

Maintainer: Nicole Kraemer <nkraemer@cs.tu-berlin.de>

References

Kraemer, N., Braun, M.L. (2007) "Kernelizing PLS, Degrees of Freedom, and Efficient Model Selection", Proceedings of the 24th International Conference on Machine Learning, Omni Press, 441 - 448

See Also

kernel.pls, kernel.pls.cv, kernel.pls.ic,linear.pls

Examples

# to do

[Package plsdof version 0.1-1 Index]