|
Activity Number:
|
395
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Noether Award Committee
|
| Abstract - #307699 |
|
Title:
|
Nonparametric Hierarchical Models
|
|
Author(s):
|
Ciprian M. Crainiceanu*+
|
|
Companies:
|
Johns Hopkins University
|
|
Address:
|
615 N. Wolfe St. E3636, Baltimore, MD, 21205,
|
|
Keywords:
|
signal extraction ; hierarchical smoothing ; penalized splines
|
|
Abstract:
|
We develop the nonparametric hierarchical inferential framework with focus on model estimation and testing. Two complementary methodologies are discussed and implemented for scientific and geometric signal extraction. We identify, describe and solve a new measurement error problem generated by the hierarchical smoothing process when signals are used in second level analyses. Our research was motivated by a large (6,400 subjects) longitudinal study of electro encephalographic (EEG) signals during sleep where the natural hierarchy is patient/group or cluster/visit. The design of our methods and use of low rank penalized splines make our computations tractable.
|
- 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 |
