|
Activity Number:
|
276
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #309864 |
|
Title:
|
High-Dimension, Low Sample Size (HDLSS) Data Asymptotics
|
|
Author(s):
|
Xuxin Liu*+
|
|
Companies:
|
The University of North Carolina at Chapel Hill
|
|
Address:
|
Dept. of Statistics and Operations Research, Chapel Hill, NC, 27514,
|
|
Keywords:
|
High Dimensional data ; Microarray ; Batch adjustment
|
|
Abstract:
|
We present the HDLSS asymptotics, in the sense that the dimension goes to infinity and the sample sizes are fixed. The geometric structure of the data cloud becomes very simple under HDLSS asymptotics. We compare two micro-array data combination methods, PAM and DWD. These two methods have very different HDLSS asymptotic properties. We give the conditions for the consistency and inconsistency of these two methods for the combination of two data sets with unbalanced sample sizes.
|
- 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 2007 program |
