Back to search

University of Washington

A resampling approach to clustering with confidence

Abstract

dc:description.abstract

We propose a method for estimating the number of groups in a data set. Our method is an extension of Generalized Single Linkage clustering (GSL) (Stuetzle and Nugent 2010), a nonparametric clustering method based on the premise that groups in the data correspond to modes of the underlying data density. GSL starts with a nonparametric density estimate. It recursively splits the data into high density regions separated by valleys. The leaves of the resulting cluster tree correspond to modes of the density estimate. The problem is that nonparametric density estimates tend to have spurious modes due to sampling variability, giving rise to spurious splits in the cluster tree. We propose a resampling method aimed at assessing the significance of splits and a way of constructing a cluster tree making only significant splits. The only parameter is the significance level. Our method can identify highly non-linear groups. Simulation experiments suggest that the method is very conservative, which may explain its low power.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Chiam, Yuan
Advisor dc:contributor.advisor
  • Stuetzle, Werner

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Copyright is held by the individual authors.
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1773/20906

Chain of custody

source
Harvested from
University of Washington
Base URL
digital.lib.washington.edu/server/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Chiam, Yuan. A resampling approach to clustering with confidence. 2012. http://hdl.handle.net/1773/20906