Description Usage Arguments Value References Examples

Fitting reduced-rank ridge regression with given rank and shrinkage penalty This is a modification of rrs.fit in rrpack version 0.1-6. In order to handle extremely large q = ncol(Y), generation of a q by q matrix is avoided.

1 |

`Y` |
a matrix of response (n by q) |

`X` |
a matrix of covariate (n by p) |

`nrank` |
an integer specifying the desired rank |

`lambda` |
tunging parameter for the ridge penalty |

`coefSVD` |
logical indicating the need for SVD for the coeffient matrix int the output |

S3 `rrr`

object, a list consisting of

`coef` |
coefficient of rrs |

`coef.ls` |
coefficient of least square |

`fitted` |
fitted value of rrs |

`fitted.ls` |
fitted value of least square |

`A` |
right singular matrix |

`Ad` |
sigular value vector |

`nrank` |
rank of the fitted rrr |

Mukherjee, A. and Zhu, J. (2011) Reduced rank ridge regression and its kernal extensions.

Mukherjee, A., Chen, K., Wang, N. and Zhu, J. (2015) On the degrees of
freedom of reduced-rank estimators in multivariate
regression. *Biometrika*, 102, 457–477.

1 2 3 |

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.