enetpath: enetpath

View source: R/Regression.R

enetpathR Documentation

enetpath

Description

enethpath computes the elastic net (EN) regularization path (over grid of penalty parameter values). Uses pathwise CCD algorithm.

Usage

enetpath(y, X, alpha = 1, L = 100, eps = 1e-04, intcpt = TRUE,
  printitn = 0)

Arguments

y

: Numeric data vector of size N x 1 (output, respones)

X

: Nnumeric data matrix of size N x p. Each row represents one observation, and each column represents one predictor (feature).

alpha

: Numeric scalar, elastic net tuning parameter in the range [0,1]. If not given then use alpha = 1 (Lasso)

L

: Positive integer, the number of lambda values EN/Lasso uses. Default is L=100.

intcpt:

Logical flag to indicate if intercept is in the model. Default = True

eps:

Positive scalar, the ratio of the smallest to the largest Lambda value in the grid. Default is eps = 10^-4.

printitn:

print iteration number (default = 0, no printing)

Value

B : Fitted EN/Lasso regression coefficients, a p-by-(L+1) matrix, where p is the number of predictors (columns) in X, and L is the number of Lambda values. If intercept is in the model, then B is (p+1)-by-(L+1) matrix, with first element the intercept.

stats : list with following fields:

Lambda

lambda parameters in ascending order

MSE

Mean squared error (MSE)

BIC

Bayesian information criterion values for each lambda

Note

file in Regression.R

Examples

y <- c(0.5377   , 1.8339   ,-2.2588 ,   0.8622,    0.3188)
x <- c(-1.3077  , -0.4336,    0.3426   , 3.5784,    2.7694)

enetpath(y, matrix(c(x, x), nrow = 5, ncol = 2))


Mufabo/Rrobustsp documentation built on June 11, 2022, 10:41 p.m.