Function to fit least angle regression path of solution for the elastic net.

Share:

Description

Function to fit least angle regression path of solution for the elastic net.

Usage

1
lars.en(x, y, lambda2,normalize=TRUE)

Arguments

x

N by p matrix of predictors

y

N-vector of outcome values

lambda2

Value of L2 penalty parameter

normalize

Should columns of x be standardized?

Details

This function estimates the least angle regression path of solution for Ll-penalized (lasso) logistic regression and the Cox proportional hazards model, using the R functions enpath and coxpath. These latter functions use the predictor-corrector strategy devised by Park and Hastie (2007).

Value

beta

Matrix whose rows of contain the estimated coefficients for each lambda value

larsobj

Result of call to lars on augmented data

mx

Column means of x

sdx

Column standard deviations of x

normalize

Value of normalize argument in call to lars.en

lambda

Values of lambda used

lambda2

Value of lambda2 used

act

Actions (predictor added) at each step

maxp

Maximum number of predictors entered

call

Call to lars.en

Author(s)

Rob Tibshirani

References

Zou, H. and Hastie, Trevor (2005) Regularization and Variable Selection via the Elastic Net. JRSSB 301-320,

Park, M. Y. & Hastie, T. (2007). l1-regularization path algorithm for generalized linear models, Journal of the Royal Statistical Society Series B 69(4),

See Also

predict.lars, covTest

Examples

1
2
3
4
5
6
7
set.seed(432)
x=matrix(rnorm(100*10),ncol=10)
x=scale(x,TRUE,TRUE)/sqrt(99)
beta=c(3,rep(0,9))
y=x%*%beta+.4*rnorm(100)
a=lars.en(x,y,lambda2=.5)