Session 9 : Recent Developments in the Application of Pairwise Overlap

Presenter Information/ Coauthors Information

Volodymyr Melnykov, University of Alabama - TuscaloosaFollow

Presentation Type

Invited

Student

No

Track

Methodology

Abstract

Pairwise overlap is defined as the sum of misclassification probabilities calculated for a pair of mixture components. It is useful for studying the systematic performance of clustering algorithms. Currently, existing methods allow simulating elliptically distributed data according to pre-specified overlap characteristics. An approach to simulating skewed clusters with a desired overlap is proposed. Next, an extension to measuring overlap in cluster-weighted models is discussed.

Start Date

2-7-2025 2:30 PM

End Date

2-7-2025 3:30 PM

This document is currently not available here.

Share

COinS
 
Feb 7th, 2:30 PM Feb 7th, 3:30 PM

Session 9 : Recent Developments in the Application of Pairwise Overlap

Dakota A & C (Room 250)

Pairwise overlap is defined as the sum of misclassification probabilities calculated for a pair of mixture components. It is useful for studying the systematic performance of clustering algorithms. Currently, existing methods allow simulating elliptically distributed data according to pre-specified overlap characteristics. An approach to simulating skewed clusters with a desired overlap is proposed. Next, an extension to measuring overlap in cluster-weighted models is discussed.