Statistics Seminars: Tests for large tree-structured data
14 November 2016 14:00 in CM221
I will discuss goodness-of-fit tests for data which allow for hierarchical, tree-like representations using the Continuum Random Tree (CRT) proposed by Aldous, which arises as the (invariant) continuous limit for a general class of probability models on trees. The tests rely on two different characterizations of the CRT relating to a Brownian excursion and a special class of subtrees. I will present some empirical results on the utility of the tests on binary trees obtained from agglomerative hierarchical clustering algorithms in the context of a dataset of tumour images.
Contact firstname.lastname@example.org for more information