Abstract Details
Activity Number:
|
25
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
ENAR
|
Abstract #311954
|
View Presentation
|
Title:
|
Analysis of Big Imaging Data via a Bayesian Thresholding Approach
|
Author(s):
|
Jian Kang*+
|
Companies:
|
Emory University
|
Keywords:
|
Big Data ;
NeuroImaging ;
MCMC ;
Truncated Normal Mixture
|
Abstract:
|
Motivated by the needs of performing feature selections from big imaging data, we propose a new class of thresholding priors to induce sparsity in the Bayesian paradigm. The thresholding priors can be equivalently represented through three-component mixture priors having a probability mass at zero, but it avoids the daunting posterior computations in high dimensions that are encountered by the usual two-component mixture priors. We demonstrate that the thresholding priors enjoy the advantages of both local priors and non-local priors. To make efficient posterior inference, we develop a Markov chain Monte Carlo (MCMC) algorithm and a fast approximate Bayesian computation (ABC) algorithm which can be scaled up for ultra-high dimensional data analysis. We illustrate our method and compare it with existing methods through simulation studies and a real imaging data application.
|
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.