Activity Number:
|
202
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 13, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Nonparametric Statistics*
|
Abstract - #300505 |
Title:
|
Nonparametric Multivariate Kurtosis and Tailweight Measures
|
Author(s):
|
Jin Wang*+ and Robert Serfling+
|
Affiliation(s):
|
University of Texas, Dallas and University of Texas, Dallas
|
Address:
|
, Richardson, Texas, 75083, USA , Richardson , Texas, 75083, USA
|
Keywords:
|
Nonparametric Multivariate Analysis ; Tailweight ; Kurtosis ; Peakedness
|
Abstract:
|
A new nonparametric multivariate kurtosis functional is introduced. Defined as a particular transform of the volume functional of a given median-oriented quantile function, the measure characterizes the relative difference between equiprobable volumes toward the "center" and towards the "tails," starting from the "shoulders" of the distribution. It reduces to a familiar measure in the symmetric univariate case and provides a new and intuitively appealing measure in the asymmetric univariate case. Properties of the new measure will be discussed and comparison made with several other nonparametric multivariate measures concerned with peakedness, kurtosis, and tailweight. The asymptotic behavior of sample versions will be characterized.
|
- 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 2002 program |