HierBasis-package: Nonparametric regression and high dimensional additive model...

In asadharis/HierBasis: Nonparametric Regression and Sparse Additive Modeling

Description

This package implements the HierBasis method of Haris et al. (2016). The main methods of this package can fit univariate nonparametric functions and sparse additive models.

The hierarchical penalty leads to data-driven estimates which can adapt to varying levels of complexities. It also leads to a parsimonious representation for the estimated functions.

Details

Package:	HierBasis
Type:	Package
Version:	0.8.1
Date:	2017-31-01
License:	GPL (>= 2)

The package includes the following functions:

HierBasis:	Main function for univariate nonparametric regression.
predict.HierBasis:	Generic predict function for univariate regression.
GetDoF.HierBasis:	Evaluate the degrees of freedom of fitted model.
AdditiveHierBasis:	Main function for fitting sparse additive models.
predict.addHierBasis:	Generic predict function for fitted sparse additive models.
plot.addHierBasis:	Plot estimated component functions for additive models.

Author(s)

Asad Haris, Ali Shojaie and Noah Simon

Maintainer: Asad Haris ([e-mail])

References

Haris, A., Shojaie, A. and Simon, N. (2016). Nonparametric Regression with Adaptive Smoothness via a Convex Hierarchical Penalty. Available on request by authors.

See Also

HierBasis, AdditiveHierBasis

asadharis/HierBasis documentation built on Aug. 3, 2021, 4:16 p.m.