Title: Mixture of functional graphical models with an application to ADHD data
Authors: Qihai Liu - Western Michigan University (United States)
Lucas Price - Western Michigan University (United States)
Kevin Lee - Western Michigan University (United States)
Hyun Bin Kang - Western Michigan University (United States) [presenting]
Abstract: Many scientific areas are faced with the challenge of extracting information from large complex data. As a part of such effort, a functional graphical model is developed to extract the conditional dependence structure among random functions. The mixture of functional graphical models is presented, where the random functions are from a mixture of Gaussian processes with different conditional dependence structures. An EM algorithm for finding the mixture group of each function and the conditional dependence structure will be proposed, and a BIC-based criteria for selecting an optimal number of groups will be presented. The motivation comes from an ADHD dataset, which will be discussed.