Learn R Programming

glinternet (version 1.0.12)

Learning Interactions via Hierarchical Group-Lasso Regularization

Description

Group-Lasso INTERaction-NET. Fits linear pairwise-interaction models that satisfy strong hierarchy: if an interaction coefficient is estimated to be nonzero, then its two associated main effects also have nonzero estimated coefficients. Accommodates categorical variables (factors) with arbitrary numbers of levels, continuous variables, and combinations thereof. Implements the machinery described in the paper "Learning interactions via hierarchical group-lasso regularization" (JCGS 2015, Volume 24, Issue 3). Michael Lim & Trevor Hastie (2015) .

Copy Link

Version

Install

install.packages('glinternet')

Monthly Downloads

1,053

Version

1.0.12

License

GPL-2

Maintainer

Last Published

September 3rd, 2021

Functions in glinternet (1.0.12)

glinternet

Fit a linear interaction model with group-lasso regularization that enforces strong hierarchy in the estimated coefficients
coef.glinternet

Return main effect and interaction coefficients.
predict.glinternet.cv

Make predictions from a "glinternetCV" object.
plot.glinternet.cv

Plot CV error from glinternetCV object.
predict.glinternet

Make predictions from a "glinternet" object.
glinternet.cv

Cross-validation for glinternet