A0321
Title: High dimensional general linear hypotheses under a spiked covariance model
Authors: Haoran Li - Auburn University (United States) [presenting]
Debashis Paul - University of California Davis (United States)
Jie Peng - University of California Davis (United States)
Alexander Aue - university of California Davis (United States)
Abstract: The problem of testing linear hypotheses under a multivariate regression model is considered with a high-dimensional response and spiked noise covariance. The proposed family of tests consists of test statistics based on a weighted sum of projections of the data onto the estimated latent factor directions, with the weights acting as the regularization parameters. The asymptotic normality of the test statistics is established under the null hypothesis. The power characteristics of the tests is also established, and a data-driven choice of the regularization parameters is proposed under a family of local alternatives. The performance of the proposed tests is evaluated through a simulation study. Finally, the proposed tests are applied to the Human Connectome Project data to test for the presence of associations between volumetric measurements of the human brain and behavioral variables.
