genet: Generalized Elastic Net/Bridge Penalty for GLMs

In abnormally-distributed/cvreg: Cross Validation and Robust Estimation Utilities

Description

The elastic net penalty is defined by a linear combination of lasso (L1) and ridge (L2) penalties. The generalized elastic net penalty replaces the L2 penalty with the bridge penalty (Lp).

Usage

genet(
  formula,
  data,
  family = gaussian(),
  lambda = NULL,
  alpha = 0.5,
  kappa = 1.4,
  weights = NULL,
  start = NULL,
  etastart = NULL,
  mustart = NULL,
  offset = rep(0, nobs),
  standardize = TRUE
)

Arguments

formula	a model formula.
data	a data frame
family	the glm family. defaults to gaussian().
lambda	the penalty
alpha	the mixing parameter for the lasso and bridge penalties. defaults to 0.5. 0 gives full weight to the bridge penalty, while 1 gives full weight to the lasso penalty.
kappa	the Lp norm of the bridge penalty. defaults to 1.4.
weights	an optional vector of weights to be used in the fitting process.
start	starting values for the coefficients.
etastart	starting values for the linear predictor.
mustart	starting values for the fitted values.
offset	this can be used to specify an a priori known component to be included in the linear predictor during fitting.
standardize	whether the regressors should be standardized (this is recommended) or not. defaults to TRUE.

abnormally-distributed/cvreg documentation built on May 3, 2020, 3:45 p.m.