get_edgeprobs: Compute posterior probabilities of edge inclusion from the...

In BCDAG: Bayesian Structure and Causal Learning of Gaussian Directed Graphs

Compute posterior probabilities of edge inclusion from the MCMC output

Description

This function computes the posterior probability of inclusion for each edge u -> v given the MCMC output of learn_DAG;

Usage

get_edgeprobs(learnDAG_output)

Arguments

learnDAG_output

object of class bcdag

Details

Output of learn_dag function consists of S draws from the joint posterior of DAGs and DAG-parameters in a zero-mean Gaussian DAG-model; see the documentation of learn_DAG for more details.

The posterior probability of inclusion of u -> v is estimated as the frequency of DAGs visited by the MCMC which contain the directed edge u -> v. Posterior probabilities are collected in a (q,q) matrix with (u,v)-element representing the estimated posterior probability of edge u -> v.

Value

A (q,q) matrix with posterior probabilities of edge inclusion

Author(s)

Federico Castelletti and Alessandro Mascaro

References

F. Castelletti and A. Mascaro (2021). Structural learning and estimation of joint causal effects among network-dependent variables. Statistical Methods and Applications, Advance publication.

Examples

# Randomly generate a DAG and the DAG-parameters
q = 8
w = 0.2
set.seed(123)
DAG = rDAG(q = q, w = w)
outDL = rDAGWishart(n = 1, DAG = DAG, a = q, U = diag(1, q))
L = outDL$L; D = outDL$D
Sigma = solve(t(L))%*%D%*%solve(L)
# Generate observations from a Gaussian DAG-model
n = 200
X = mvtnorm::rmvnorm(n = n, sigma = Sigma)
# Run the MCMC (Set S = 5000 and burn = 1000 for better results)
out_mcmc = learn_DAG(S = 500, burn = 100, a = q, U = diag(1,q)/n, data = X, w = 0.1,
                     fast = TRUE, save.memory = FALSE)
# Compute posterior probabilities of edge inclusion
get_edgeprobs(out_mcmc)

BCDAG documentation built on April 4, 2025, 1:41 a.m.