The likelihood of a simple graph is defined by starting with the set S_1 = {(K_1 1)}. The following procedure is then iterated to produce a set of graphs G_n of order n. At step n, randomly pick an integer k from the set {0, 1, ..., n - 1}. Now randomly pick one of graphs in S_(n - 1) (keeping the probability that it was constructed in step n - 1) and from it add a new vertex that is connected to all of k randomly selected of its existing vertices. Now merge any isomorphic graphs produced by this procedure by totalling the their probabilities. The likelihood of a graph G on n vertices is then defined as the probability that G appears in S_n.