Statistical Inference for Clustering

Abstract

In this dissertation, we develop new methods for statistical inference in the context of single- view and multi-view clustering. In the first two chapters, we consider the multi-view data setting, where multiple data sets are collected from a common set of features. We propose tests of independence between the cluster membership variables in each data view that can be applied to any combination of multivariate and network data views. In the third chapter, we propose a test of no difference in means between two clusters obtained from hierarchical clustering.