Abstract Details
Activity Number:
|
652
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 7, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
Abstract #312676
|
View Presentation
|
Title:
|
A Review on Combining Statistical Procedures in High-Dimensional Data Analysis
|
Author(s):
|
Yanjia Yu*+
|
Companies:
|
University of Minnesota, Twin Cities
|
Keywords:
|
combining statistical procedures ;
high dimensional data ;
model selection
|
Abstract:
|
One of the main interests in statistical analysis is prediction. For the same data, if we use different statistical models we might get quite different prediction results. This is especially common in high dimensional data analysis, where there is high model selection uncertainty. To reduce the variance in prediction, the idea of combining statistical procedures is proposed. Combining is popular and useful, but there is not too much thorough and up-to-date review on this topic in high-dimensional data analysis. In this paper, we review many popular approaches in combining procedures: Bayesian model averaging, information criterion based weighting methods, Bagging, random forest, and ARM, to name a few. We compare those combining procedures in simulation studies and real data examples to evaluate their performance in high-dimensional data analysis. We also summarize the algorithms and coding resources for those popular combining procedures. This review is a helpful guide for statisticians who want to use combining procedure in high-dimensional data analysis.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.