Fig. 5From: Correcting a nonparametric two-sample graph hypothesis test for graphs with different numbers of vertices with applications to connectomicsPower of the nonparametric latent distribution permutation test that uses CASE against the alternative with graphs generated from A \(\sim ER(n, 0.8^2)\) and B \(\sim ER(cn, 0.79^2)\). Error bars represent 95% confidence intervalBack to article page