Online Program Home
My Program

Abstract Details

Activity Number: 324
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
Sponsor: Section on Nonparametric Statistics
Abstract #318674
Title: Depth Functions and Classification Using Beta-Skeleton Graphs
Author(s): Yu Song*
Companies: The George Washington University
Keywords: beta-skeleton ; U-statistic ; high dimension ; distribution function ; interpoint distance

We define the beta-skeletons depths based on the probability that a point is contained within the beta -skeleton influence region of two i.i.d. random vectors. We show that the -skeleton depths are a family of statistical depth functions. We define and examine the sample beta -skeleton depth functions and show that they have desirable asymptotic properties. We also explore the beta -skeleton depth to test for the equality of the high dimensional distribution functions and classi cation. A Monte Carlo study compares the beta -skeleton test with some existing statistics.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association