Activity Number:
|
529
- SPEED: Machine Learning
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 2, 2017 : 10:30 AM to 11:15 AM
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
Abstract #325311
|
|
Title:
|
Statistical Significance of Clustering
|
Author(s):
|
Purvasha Chakravarti* and Larry Wasserman and Sivaraman Balakrishnan
|
Companies:
|
Carnegie Mellon University and Carnegie Mellon and Department of Statistics, CMU
|
Keywords:
|
Clustering ;
k means ;
Power ;
Hypothesis Testing
|
Abstract:
|
In clustering, it is critical to separate real clusters from noise. Liu et al (2012) proposed an approach based on iterative hypothesis testing. We study the theoretical properties of their procedure. In particular, we find the asymptotic limiting distribution of the test, which allows us to characterize the power. We also consider some simulated examples.
|
Authors who are presenting talks have a * after their name.