A1228
Title: Bayesian estimation of covariate assisted principal regression for brain functional connectivity
Authors: Hyung Park - New York University School of Medicine (United States) [presenting]
Abstract: A Bayesian reformulation of covariate-assisted principal (CAP) regression is presented, which aims to identify components in covariance matrices that are associated with covariates in a regression framework. A geometric formulation and reparameterization of individual covariance matrices in their tangent space are introduced. By mapping the covariance matrices to the tangent space, Euclidean geometry is leveraged to perform posterior inference. This approach enables joint estimation of all parameters and uncertainty quantification within a unified framework, combining dimension reduction for covariance matrices and regression model estimation. To assess the performance of the proposed method, simulation studies are conducted to evaluate its accuracy and efficiency. The method is also applied to analyze associations between covariates and brain functional connectivity, utilizing data from the Human Connectome Project.
