B0706
Title: Two sample testing for diffusion tensor imaging data
Authors: Gina-Maria Pomann - Duke University (United States) [presenting]
Ana-Maria Staicu - North Carolina State University (United States)
Sujit Ghosh - North Carolina State University (United States)
Abstract: Motivated by a natural history imaging study, we present a non-parametric testing procedure for testing the null hypothesis that two samples of curves observed at discrete grids and with noise have the same underlying distribution. We use functional principal components-based methods to develop a test for the equality of the distributions of two samples of curves, when their eigenfunctions are the same. The approach reduces the dimensionality of the testing problem in a way that enables the application of traditional nonparametric univariate testing procedures. This results in a procedure that is not only computationally efficient but also allows for a variety of sampling designs. This methodology is applied to a diffusion tensor imaging (DTI) study, where the objective is to statistically compare white matter tract profiles between healthy individuals and multiple sclerosis patients, as assessed by conventional DTI measures.
