This paper proposes a cluster-based inferential procedure. Observations are grouped into clusters which are learned using an unsupervised hierarchical clustering algorithm given a known similarity measure. We use a randomization inference procedure to perform cluster-based inference on the learned clusters. We give conditions under which our procedure asymptotically attains correct size. This paper is joint work with Jianfei Cao, Christian Hansen, Lucciano Villacorta.
Personal website of Damian Kozbur