English

Cluster Analysis via Random Partition Distributions

Methodology 2021-06-08 v1

Abstract

Hierarchical and k-medoids clustering are deterministic clustering algorithms based on pairwise distances. Using these same pairwise distances, we propose a novel stochastic clustering method based on random partition distributions. We call our method CaviarPD, for cluster analysis via random partition distributions. CaviarPD first samples clusterings from a random partition distribution and then finds the best cluster estimate based on these samples using algorithms to minimize an expected loss. We compare CaviarPD with hierarchical and k-medoids clustering through eight case studies. Cluster estimates based on our method are competitive with those of hierarchical and k-medoids clustering. They also do not require the subjective choice of the linkage method necessary for hierarchical clustering. Furthermore, our distribution-based procedure provides an intuitive graphical representation to assess clustering uncertainty.

Keywords

Cite

@article{arxiv.2106.02760,
  title  = {Cluster Analysis via Random Partition Distributions},
  author = {David B. Dahl and Jacob Andros and J. Brandon Carter},
  journal= {arXiv preprint arXiv:2106.02760},
  year   = {2021}
}
R2 v1 2026-06-24T02:51:32.710Z