This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 76
Type: Contributed
Date/Time: Sunday, August 1, 2010 : 4:00 PM to 5:50 PM
Sponsor: Section on Nonparametric Statistics
Abstract - #308942
Title: Asymptotically Sufficient Statistics in Nonparametric Regressions with Correlated Errors
Author(s): Andrew Carter*+
Companies: University of California, Santa Barbara
Address: Dept of Statistics, Santa Barbara, CA, 93106-6110,
Keywords: nonparametric regression ; asymptotically sufficient statistics ; asymptotics
Abstract:

Asymptotically sufficient statistics can provide a simplification of the inference in a problem without losing an appreciable amount of information about the parameters of interest. In a nonparametric regression where we want to estimate a smooth mean function in the presence of correlated noise, there are asymptotically sufficient statistics with a smaller dimension than the original observations that may also have a simplified covariance structure. We consider two possible types of correlation: short-range correlation where the asymptotically sufficient statistics are nearly uncorrelated, and long-range correlation where the covariance structure persists in the approximation. In either case, these sufficient statistics can be used to compare the nonparametric regression experiments to continuous Gaussian process experiments.


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.