obsDAG: A DAG function for observational data

In intdag: Reconstruction of a Directed Acyclic Graph with Interventions

Description

This function allows you to learn the DAG structure from observational data

Usage

obsDAG(X, lambda, tau, rho = 1, A_NZ0 = NULL, A0 = NULL,
  opts.tol = 1e-04, maxIter = 1000)

Arguments

X	The n by p data matrix
lambda	tuning parameter for the first penalty of the adjacency matrix
tau	tuning parameter of the TLP function
rho	the ADMM penalty parameter, default is 1
A_NZ0	An p by p matrix indicating nonzero elements as initial values
A0	An p by p matrix as initial values for A
opts.tol	Tolerance for convergence
maxIter	maximum number of iterations in ADMM loop

Value

Estimated adjacency matrix

Examples

p <- 10
amat <- matrix(0, p, p)
amat[2:p, 1] <- 1
Sig <- seq(1, 0.5, length.out=p)
X <- rmvDAG_obs(100, amat, Sig)
out <- obsDAG(X, 5, 0.01)

intdag documentation built on Oct. 9, 2019, 9:05 a.m.