Activity Number:
|
152
- Recent Development in Sufficient Dimension Reduction
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, July 31, 2017 : 10:30 AM to 12:20 PM
|
Sponsor:
|
International Statistical Institute
|
Abstract #322635
|
|
Title:
|
On Sufficient Dimension Reduction with Missing Responses Through Estimating Equations
|
Author(s):
|
Yuexiao Dong* and Qi Xia and Chengyong Tang
|
Companies:
|
Temple University and Temple University and Temple University
|
Keywords:
|
Complete-case analysis ;
Inverse probability weighting ;
Kernel inverse regression ;
Linear conditional mean ;
Missing at random
|
Abstract:
|
A linearity condition is required for all the existing sufficient dimension reduction methods that deal with missing data. Since Li and Dong (2009) and Ma and Zhu (2012), several procedures based on estimating equations have been proposed to remove the linearity condition for sufficient dimension reduction without missing data. In this paper, we propose two new estimating equation procedures to handle missing response in sufficient dimension reduction: the complete-case estimating equation approach and the inverse probability weighted estimating equation approach. The consistency of the estimators are established, and their superb finite sample performances are demonstrated through extensive numerical studies as well as a real data analysis of the New Zealand mussel data.
|
Authors who are presenting talks have a * after their name.