|
Activity Number:
|
271
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Graphics
|
| Abstract - #305849 |
|
Title:
|
Graph Theoretic Methods for Cluster Verification
|
|
Author(s):
|
Bernard Harris*+
|
|
Companies:
|
University of Wisconsin
|
|
Address:
|
1226 Brookwood Rd, Madison, WI, 53711-3118,
|
|
Keywords:
|
|
|
Abstract:
|
The purpose of this investigation is to determine if a set of data values contains clusters or if the apparent clusters are "false positives." Graph theoretic methods are introduced and their efficacy as criteria are studied. Data sets in k-dimensional Euclidean space are studied. Hilbert space valued data can also be analyzed in this manner. Similar methods are suggested for data mining, where, because of the large volumes of data studied, "false positives" are frequently encountered.
|
- 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 2009 program |
