A0253
Title: Covariance outcome modelling via covariate assisted principal regression
Authors: Xi Luo - Univ of Texas Health Science Center at Houston (United States) [presenting]
Yi Zhao - Indiana University (United States)
Brian Caffo - Johns Hopkins University (United States)
Bingkai Wang - Johns Hopkins University (United States)
Abstract: Modelling the variations in covariance matrix outcomes is becoming an important topic in many fields, including financial and neuroimaging analysis. The problem of regressing covariance matrices on vector covariates collected from each observational unit in cross-sectional or longitudinal settings is considered. The aim is to review the proposed (generalized) linear model framework and recent advances for this problem. The focus will be on mathematical formulation, algorithmic development, and asymptotic properties. Accuracy and robustness will be demonstrated using extensive simulations. The proposals were also applied to a few large-scale resting-state functional magnetic resonance imaging studies, and the specific human brain network changes associated with covariates were identified.
