This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
Abstract Details
Activity Number:
|
25
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, August 1, 2010 : 2:00 PM to 3:50 PM
|
Sponsor:
|
IMS
|
Abstract - #306561 |
Title:
|
Nonparametric Regression with Missing Data
|
Author(s):
|
Sam Efromovich*+
|
Companies:
|
UT Southwestern Medical Center
|
Address:
|
800 West Campbell Rd , Richardson, TX, 75080,
|
Keywords:
|
Adaptation ;
Asymptotic ;
MAR ;
Small Sample
|
Abstract:
|
Regression based on missing at random (MAR) responses is a familiar topic in the missing data literature. Imputation is the traditional remedy. What will be if inadvertently predictors, corresponding to missing responses, are also lost and only ``complete-case'' pairs of observations are available? It is well documented in the literature that a complete-case analysis is generally inadmissable. It is proved that, contrary to this general rule, in a nonparametric regression this approach implies the same sharp minimax mean integrated squared error (MISE) convergence as by a sharp minimax estimator based on the underlying MAR sample. Then ``the table is turned around'' and a less studied, even in the parametric and semiparametric literature, problem of missed at random (MAR) predictors is explored. Both methodology and methods of estimation are presented.
|
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.