Abstract Details
|
Activity Number:
|
508
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2014 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
|
Abstract #312443
|
View Presentation
|
|
Title:
|
Searching for Local Holes in Multivariate Data
|
|
Author(s):
|
Woollcott Smith*+
|
|
Companies:
|
Temple University
|
|
Keywords:
|
Density estimation ;
Change of measure ;
Truncation ;
Multi-dimensional graphics
|
|
Abstract:
|
A search procedure is developed to find a local anomaly (hole) where there are fewer data points than expected, given the surrounding region. The basic idea is to optimize a multivariate Gaussian weighting function that reweights the data so that the center of the reweighted data is located near the center of the hole. The reweighting procedure is motivated by a standard change of measure argument for Gaussian distributions. These ideas lead to new graphical displays of local n-dimensional holes. The classical "pollen data" and other applications are used to illustrate the procedure and the graphical display methods.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.