B0526
Title: Parsimonious multivariate spatial regression
Authors: Hossein Moradi Rekabdarkolaee - South Dakota State University (United States) [presenting]
Abstract: Dimension reduction provides a useful tool for analyzing high dimensional data. The recently developed Envelope method is a parsimonious version of the classical multivariate regression model by identifying a minimal reducing subspace of the responses. We introduce an extension of the envelope, called spatial envelope method, for dimension reduction in the presence of dependencies across space. We studied the effectiveness o this approach through a simulation study and data analysis.
