The average <i>p</i>-values obtained using bottleneck, GH, KS, maximum gap, and ETL based statistics for small (<i>p</i> = 10) and large (<i>p</i> = 100) network settings.

There were 6 networks in each group. The p-values smaller than 0.01 indicate that the corresponding method can identify network differences at a 99% confidence level.