JSM 2011 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Abstract Details

Activity Number: 585
Type: Contributed
Date/Time: Wednesday, August 3, 2011 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Mining
Abstract - #300837
Title: Consistent Selection of the Number of Clusters via Clustering Stability
Author(s): Junhui Wang*+
Companies: University of Illinois at Chicago
Address: , , ,
Keywords: Cluster analysis ; Cross validation ; k-means ; Selection consistency ; Spectral clustering ; Stability
Abstract:

In cluster analysis, one of the major challenges is to estimate the number of clusters. Most existing approaches focus on the within- and between cluster dissimilarities measured by various forms of distance. In this talk, I will present a novel selection criterion that is applicable to all kinds of clustering algorithms, distance-based or non-distance-based. The key idea is to select the number of clusters such that the corresponding clustering algorithm has the smallest instability. The clustering instability measures the robustness of any given clustering algorithm against the randomness in the sampling. Numerical examples will be provided to demonstrate the effectiveness of the proposed selection criterion. Asymptotic selection consistency of the proposed selection criterion will also be discussed.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2011 program




2011 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.