Inference on Two-Sample Covariance Difference for Large-Scale Functional Data

In this study, we introduce an inferential procedure for assessing the covariance difference between two-samples of large-scale functional data, utilizing a computationally efficient multiplier bootstrap approach.In contrast to the existing method that focuses exclusively on a testing procedure, our approach starts by establishing a confidence region for the covariance difference under fairly flexible conditions.This leads not only to a more powerful test but also to an accessible estimated powe