Tests for separability in nonparametric covariance operators of random surfaces

Abstract

The assumption of separability of the covariance operator for a random image or hypersurface can be of substantial use in applications, especially in situations where the accurate estimation of the full covariance structure is unfeasible, either for computational reasons, or due to a small sample size. However, inferential tools to verify this assumption are somewhat lacking in high-dimensional or functional {data analysis} settings, where this assumption is most relevant. We propose here to test separability by focusing on $K$-dimensional projections of the difference between the covariance operator and a nonparametric separable approximation. The subspace we project onto is one generated by the eigenfunctions of the covariance operator estimated under the separability hypothesis, negating the need to ever estimate the full non-separable covariance. We show that the rescaled difference of the sample covariance operator with its separable approximation is asymptotically Gaussian. As a by-product of this result, we derive asymptotically pivotal tests under Gaussian assumptions, and propose bootstrap methods for approximating the distribution of the test statistics. We probe the finite sample performance through simulations studies, and present an application to log-spectrogram images from a phonetic linguistics dataset.

47 pages, 10 figures, 4 tables

References in corpus (5)

• The Statistical Analysis of fMRI Data
• Evaluating stationarity via change-point alternatives with applications to fMRI data
• Review of Functional Data Analysis
• Testing separability of space--time functional processes
• Functional Principal Components Analysis of Spatially Correlated Data

Cited by in corpus (9)

• Partial Separability and Functional Graphical Models for Multivariate Gaussian Processes
• Recent Developments in Complex and Spatially Correlated Functional Data
• A test of weak separability for multi-way functional data, with application to brain connectivity studies
• Testing separability of space--time functional processes
• CovNet: Covariance Networks for Functional Data on Multidimensional Domains
• Testing and Support Recovery of Correlation Structures for Matrix-Valued Observations with an Application to Stock Market Data
• Test of Weak Separability for Spatially Stationary Functional Field
• Paired Test of Matrix Graphs and Brain Connectivity Analysis
• Profile and Globe Tests of Mean Surfaces for Two-Sample Bivariate Functional Data