Given a directed graph G, global Markov states that A is independent of B given C for every triple of sets of vertices A, B, and C, such that A and B are d-separated by C (in the graph G).
The global independent statements are computed using the Bayes ball algorithm, as described in the paper "Bayes-Ball: The Rational Pastime (for Determining Irrelevance and Requisite Information in Belief Networks and Influence Diagrams)" by Ross D. Shachter.
i1 : D = digraph {{a,{b,c}}, {b,{c,d}}, {c,{}}, {d,{}}} o1 = Digraph{a => set {b, c}} b => set {c, d} c => set {} d => set {} o1 : Digraph |
i2 : L = globalMarkov D o2 = {{{a, c}, {d}, {b}}} o2 : List |