This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
Abstract Details
Activity Number:
|
426
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
|
Sponsor:
|
International Chinese Statistical Association
|
Abstract - #308266 |
Title:
|
Estimation of Mean Vector Based on Stein Estimator
|
Author(s):
|
Tianyuan Tang*+
|
Companies:
|
The University of Hong Kong
|
Address:
|
Rm715 St.john's College, Hong Kong, International, , Hong Kong
|
Keywords:
|
Stein Estimator ;
bootstrap ;
m out of n bootstrap ;
sample mean ;
coverage accuracy ;
confidence interval
|
Abstract:
|
For estimation of a d-variate mean vector mu based on random sample of size n drawn from a distribution F, a generalized Stein Estimator T may be defined which shrinks the sample mean towards a proper linear subspace L. Theoretically, the limit distribution of the product of the squared root of n and (T-mu) depends on where mu is. The conventional bootstrap method fails to be consistent when mu lies on L. And the m out of n bootstrap method fails to work when mu moves quite close to L. To investigate empirically how Stein Estimator works on this problem, we carry out simulations using bootstrap method and calculate the coverage accuracy and the expected size of the confidence interval. And we compare it with the simulation results which are carried out based on the conventional estimator-the sample mean. We will also look into remedy of m out of n bootstrap method to solve this problem
|
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.