Abstract #301467

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301467
Activity Number: 378
Type: Contributed
Date/Time: Wednesday, August 6, 2003 : 12:00 PM to 1:50 PM
Sponsor: Section on Nonparametric Statistics
Abstract - #301467
Title: Bootstrap Test for Directional Multivariate Outliers
Author(s): Abu M. Minhajuddin*+ and William R. Schucany and Wayne A. Woodward
Companies: Southern Methodist University and Southern Methodist University and Southern Methodist University
Address: Deaprtment of Statistical Scinece, Dallas, TX, 75275-0332,
Keywords: bootstrap ; outlier ; multivariate ; positive orthant
Abstract:

It can be relevant for practitioners to assess whether a new point is an outlier, given sample observations from a distribution in p dimensions. It is ocassionally of interest to identify outliers in one direction, such as in a cone like the positive orthant. Suppose a potential outlier with p variables is observed and that a training sample of n observations on these p variables is also available. Existing procedures in this area identify outlying points in every direction including the cone, i.e., nondirectional. A new bootstrap procedure is proposed to identify outliers restricted to a p-dimensional cone. The new procedure, being nonparametric in nature, requires minimal distributional assumptions. Simulation results show that for a moderate sample size, the bootstrap test performs well for multivariate normal data, as well as for non-normal, skewed data.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003