CMStatistics 2022: Start Registration
View Submission - CMStatistics
B1580
Title: Cross-scale dependence based on multi-resolution analysis of multivariate time series with application to EEG data Authors:  Haibo Wu - King Abdullah University of Science and Technology (Saudi Arabia) [presenting]
Marina Knight - University of York (United Kingdom)
Hernando Ombao - King Abdullah University of Science and Technology (KAUST) (Saudi Arabia)
Abstract: The goal is to develop a novel statistical approach to characterizing functional interactions between channels in a brain network. Wavelets are effective for capturing transient properties of non-stationary signals. Wavelets give a multi-scale decomposition of signals and, thus, can be few for studying potential cross-scale interactions between signals. We develop scale-specific sub-processes of a multivariate locally stationary wavelet stochastic process. Under this proposed framework, a novel cross-scale dependence measure and its estimation are developed, and it provides a measurement for the dependence structure of components at different scales of multivariate time series. Extensive simulation studies are conducted to demonstrate the theoretical properties of the model hold true in practice. The proposed cross-scale analysis is applied to the electroencephalogram (EEG) data to study alterations in the functional connectivity structure in children diagnosed with attention deficit hyperactivity disorder (ADHD). Our approach identified some interesting cross-scale interactions between channels in the brain network. The proposed framework can be applied to other signals.