gforce.scio: SCIO Estimator.

In GFORCE: Clustering and Inference Procedures for High-Dimensional Latent Variable Models

Description

Estimate the precision matrix with the SCIO estimator. This algorithm is due to Liu and Luo (2012). The implementation follows the active set strategy also used in the SCIO package.

Usage

gforce.scio(C, lambda, k = NULL, eps = 10^-6, max_iter = 10000,
  R_only = FALSE)

Arguments

C	a d x d numeric matrix. This is the matrix of which we seek the inverse.
lambda	a numeric. This is the sparsity penalty parameter.
k	an integer. Indicates the column of the inverse to compute.
eps	a numeric. A threshold used as a stopping criterion.
max_iter	an integer. The max number of iterations of the SCIO algorithm.
R_only	logical expression. If R_only == FALSE, then the included native code implementation will be used. Otherwise, an R implementation is used.

Value

a d dimensional numeric vector that is the kth column of the inverse of C.

References

T. Cai, W. Liu and X. Luo. A constrained l1 minimization approach to sparse precision matrix estimation. Journal of the American Statistical Association, 2011.

Examples

C <- diag(5)
theta_1 <- gforce.scio(C,0.01,1)

GFORCE documentation built on May 2, 2019, 3:44 a.m.