RegularizedSCA (version 0.5.4)

maxLGlasso: An algorithm for determining the smallest values for Lasso and Group Lasso tuning parameters that yield all zeros.

Description

maxLGlasso identify the minimum value for Lasso and Group Lasso tuning parameters that lead to an estimated P matrix with all of its elements equal 0. This minimum value is thus the maximum value (the boundary) that users should consider for Lasso and Group Lasso. Note that the algorithm is based on the "component" method; see sparseSCA.R

Usage

maxLGlasso(DATA, Jk, R)

Arguments

DATA

The concatenated data block, with rows representing subjects.

Jk

A vector. Each element of this vector is the number of columns of a data block.

R

The number of components.

Value

Glasso

The maximum value for Group Lasso tuning parameter.

Lasso

The maximum value for Lasso tuning parameter.

References

Hastie, T., Tibshirani, R., & Wainwright, M. (2015). Statistical learning with sparsity. CRC press.

Examples

# NOT RUN {
DATA1 <- matrix(rnorm(50), nrow=5)
DATA2 <- matrix(rnorm(100), nrow=5)
DATA <- cbind(DATA1, DATA2)
Jk <- c(10, 20) 
results <- maxLGlasso(DATA, Jk, R=5)
maxGLasso <- results$Glasso
maxLasso <- results$Lasso
# }