/gslope

Sparse Gaussian graphical models with Sorted L-One Penalized Estimation

Primary LanguageR

gSLOPE: sparse precision matrix estimation with Sorted L-One Penalizaed Estimation (SLOPE)

Travis build status

gSLOPE is an R package that estimates a sparse precision matrix based on regularization by the SLOPE.

Installation

Run the following code in R console to download the latest development version from Github:

if (!require(devtools)) {
  install.packages('devtools')
}
devtools::install_github("StatsIMUWr/gslope")

Usage

The main function of the package is gslope. It estimates the precision matrix . summary and plot methods are available. Details can be found in documentation online.

library(gslope)

d = gslope(mtcars)
summary(d)
coef(d)
graph_plot(d)
plot(d, col = "navy", plt = "corr")
plot(d, plt = "precision")