This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 636
Type: Contributed
Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract - #309259
Title: Identifying General-Shaped Clusters Using the k-Means Algorithm
Author(s): Anna D. Peterson*+ and Ranjan Maitra and Arka Ghosh
Companies: Iowa State University and Iowa State University and Iowa State University
Address: 1640 Carroll Ave, Ames, IA, 50010, USA
Keywords: k-means ; single linkage ; clustering

The objective of clustering is to separate observations into groups such that observations within each group are similar in some sense but different from observations in other groups. We present a computationally practical non-parametric clustering approach to identify general-shaped clusters that is applicable to large datasets and multiple dimensions. Specifically, we first fit a k-means algorithm to the dataset assuming a very large number of clusters K > (presumably much larger than the true number of clusters). The advantage of using k-means is its superior computational efficiency on large datasets, however, the algorithm is designed to identify homogeneous spherically-shaped clusters in an ideal situation. We therefore identify general-shaped clusters by using a separability index to merge groups that are close together. The resulting clustering is our final derived grouping.

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 2010 program

2010 JSM Online Program Home

For information, contact or phone (888) 231-3473.

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