dantzig.selector: Dantzig selector

In fastclime: A Fast Solver for Parameterized LP Problems, Constrained L1 Minimization Approach to Sparse Precision Matrix Estimation and Dantzig Selector

Description

Function used to select the solution path for a given lambda

Usage

dantzig.selector(lambdalist, BETA0, lambda)

Arguments

lambdalist	lambdalist is the length validn decrementing path of the lambda solution values. It is obtained from the dantzig function.
BETA0	BETA0 is a d by validn matrix where each column has an estimated regression coefficient vector given a given lambda interval. It is obtained from the dantzig function.
lambda	lambda is the lambda solution value the user wishes to estimate a regression coefficient vector with.

Details

Finds the estimated regression coefficient vector associated with a given lambda

Value

beta0

beta0 is the estimated regression coefficient vector for the given lambda.

Author(s)

Di Qi, Haotian Pang
Maintainer: Di Qi <[e-mail]>

See Also

dantzig

Examples

# generate data
a = dantzig.generator(n = 200, d = 100, sparsity = 0.1)

# regression coefficient estimation
b = dantzig(a$X0, a$y, lambda = 0.1, nlambda = 100)

# estimated regression coefficient vector
c = dantzig.selector(b$lambdalist, b$BETA0, 15)

fastclime documentation built on May 2, 2019, 1:06 p.m.