This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
Abstract Details
|
Activity Number:
|
460
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 4, 2010 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
| Abstract - #308037 |
|
Title:
|
Problems in Shape-Constrained Function Estimation Involving Correlated Errors
|
|
Author(s):
|
Mary Meyer*+
|
|
Companies:
|
Colorado State University
|
|
Address:
|
Colorado State University Dept. of Statistics, Fort Collins, CO, 80523,
|
|
Keywords:
|
time series ;
spatial models ;
trend estimation ;
variogram ;
covariance function ;
monotone
|
|
Abstract:
|
Smooth function estimation with shape restrictions is useful in a variety of applications. In this talk we look at various problems involving correlated error structures, focusing on two examples. First, we consider the problem of estimating a surface with spatially correlated errors. It is known if the covariance function is decreasing and convex, it is "valid,'' i.e., provides a positive-definite matrix. Using only shape and smoothness assumptions provides a very flexible family of covariance functions that is guaranteed to be valid. Second, we consider estimation of time series trend. Nonparametric estimators have a hard time distinguishing between "wiggly" trends and long-memory error structure, but when a shape restriction such as monotonicity is imposed, the problem of confounding between correlated noise and trend is virtually eliminated.
|
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 2010 program
|
2010 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.