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:
|
646
|
Type:
|
Topic Contributed
|
Date/Time:
|
Thursday, August 4, 2011 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract - #301929 |
Title:
|
Model-Based Clustering With A Likelihood-Tuned Density Estimator
|
Author(s):
|
Yeojin Chung*+ and Bruce George Lindsay
|
Companies:
|
University of California at Berkeley and Penn State University
|
Address:
|
525 REd Oak Ave, Albany, CA, 94706, US
|
Keywords:
|
clustering ;
kernel density estimator ;
model-based clustering
|
Abstract:
|
We extend the density-based clustering algorithm proposed by Li et al. (2007), which iteratively searched a local maximum of a kernel density estimator. If some observations climbed up to the same mode, they are merged into a cluster. We have developed an EM type procedure to improve the kernel density estimator via a nonparametric mixture model. As a result of this procedure, we obtained a new nonparametric density estimator and investigated its asymptotic and finite sample properties. This new density estimator is superior to the kernel density estimator in mode detection of a two gaussian-mixture densities. We apply our new density estimator to clustering algorithm and compare with the results based on the kernel density estimator.
|
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.