Fig. 2From: A new fast method for inferring multiple consensus trees using k-medoidsClassification performances of the four versions of our k-medoids tree clustering algorithm in terms of ARI with respect to the number of clusters, ranging from 2 to 10. The four tested versions of our algorithm were those based on: 1) SH with RF (◇), 2) CH with RF (×), 3) SH with RF squared (□) and 4) CH with RF squared (). The coalescence rate parameter in the HybridSim program was fixed to 5 in this simulation. The presented results are the averages taken over all considered numbers of tree leavesBack to article page