|
Activity Number:
|
324
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #318891
|
|
|
Title:
|
Conditional Variable Screening with Trace Pursuit
|
|
Author(s):
|
Lei Huo* and Xuerong Wen and Zhou Yu and Lu Lin
|
|
Companies:
|
Missouri University of Science and Technology and Missouri University of Science and Technology and East China Normal University and Shandong University
|
|
Keywords:
|
variable screening ;
trace pursuit ;
partial sliced inverse regression ;
, high dimension data
|
|
Abstract:
|
As the development of science and technology, high dimension data problems become more common and more complicated in different research areas. Here we propose a model free method, partial trace pursuit, to do variable screening for high dimension data with both quantitative and categorical predictor variables by extending trace pursuit method proposed by Zhou Yu (2015). We show how the partial method improve the variable screening process by different simulation cases and real data analysis.
|
Authors who are presenting talks have a * after their name.
