This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 629
Type: Contributed
Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
Sponsor: ENAR
Abstract - #309272
Title: Application of Sparse PCA via Regularized SVD to Neuroimaging Data
Author(s): Bedda L. Rosario*+ and Lisa A. Weissfeld and Julie C. Price
Companies: University of Pittsburgh and University of Pittsburgh and University of Pittsburgh
Address: PET Facility UPMC, PUH B-938 , Pittsburgh, PA, 15213,
Keywords: sparse principal component analysis ; regularized singular value decomposition ; neuroimaging
Abstract:

Principal component analysis (PCA) is a useful tool for dimension reduction of multivariate data analysis. However, in high dimensional datasets the interpretation of the principal components is often difficult since each principal component is a linear combination of all of the original variables. In most neuroimaging applications, the number of variables (voxels) is much larger than the number of samples, with the dimension of the variable space being as large as 350000 voxels. Sparse PCA via regularized singular value decomposition (sPCA-rSVD) was developed to produce modified principal components with sparse loadings (Shen et al, 2008). We applied PCA and sPCA-rSVD to positron emission tomography image data and compared the results. Our results illustrate that sPCA-rSVD can be applied to PET data for identifying important voxels and shows promise to other areas of neuroimaging.


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.