A test for separability in covariance operators of random surfaces
From MaRDI portal
Publication:2215739
DOI10.1214/19-AOS1888zbMATH Open1471.62338arXiv1710.08388MaRDI QIDQ2215739FDOQ2215739
Authors: Pramita Bagchi, Holger Dette 
Publication date: 14 December 2020
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: The assumption of separability is a simplifying and very popular assumption in the analysis of spatio-temporal or hypersurface data structures. It is often made in situations where the covariance structure cannot be easily estimated, for example because of a small sample size or because of computational storage problems. In this paper we propose a new and very simple test to validate this assumption. Our approach is based on a measure of separability which is zero in the case of separability and positive otherwise. The measure can be estimated without calculating the full non-separable covariance operator. We prove asymptotic normality of the corresponding statistic with a limiting variance, which can easily be estimated from the available data. As a consequence quantiles of the standard normal distribution can be used to obtain critical values and the new test of separability is very easy to implement. In particular, our approach does neither require projections on subspaces generated by the eigenfunctions of the covariance operator, nor resampling procedures to obtain critical values nor distributional assumptions as used by other available methods of constructing tests for separability. We investigate the finite sample performance by means of a simulation study and also provide a comparison with the currently available methodology. Finally, the new procedure is illustrated analyzing wind speed and temperature data.
Full work available at URL: https://arxiv.org/abs/1710.08388
Recommendations
- Tests for separability in nonparametric covariance operators of random surfaces
- The likelihood ratio test for a separable covariance matrix
- Permutation based testing on covariance separability
- Robust tests for scatter separability beyond Gaussianity
- A likelihood ratio test for separability of covariances
- Unbiased modified likelihood ratio tests for simple and double separability of a variance-covariance structure
- Quantifying deviations from separability in space-time functional processes
- A tuning parameter free test for properties of space-time covariance functions
- A regression perspective on generalized distance covariance and the Hilbert-Schmidt independence criterion
Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Functional data analysis (62R10)
Cites Work
- Tests for separability in nonparametric covariance operators of random surfaces
- Nonseparable, Stationary Covariance Functions for Space–Time Data
- Asymptotic Statistics
- Theoretical foundations of functional data analysis, with an introduction to linear operators
- Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference
- The likelihood ratio test for a separable covariance matrix
- Testing for separability of spatial\,-\,temporal covariance functions
- Testing separability of space-time functional processes
- A likelihood ratio test for separability of covariances
- Title not available (Why is that?)
- Title not available (Why is that?)
- Classes of linear operators. Vol. I
- Title not available (Why is that?)
- Longitudinal fMRI analysis: a review of methods
- Spatio-temporal functional regression on paleoecological data
- A test of weak separability for multi-way functional data, with application to brain connectivity studies
- Testing separability of functional time series
Cited In (13)
- Permutation based testing on covariance separability
- Random Surface Covariance Estimation by Shifted Partial Tracing
- Quantifying deviations from separability in space-time functional processes
- Testing separability of space-time functional processes
- A test of weak separability for multi-way functional data, with application to brain connectivity studies
- A novel two-way functional linear model with applications in human mortality data analysis
- A tuning parameter free test for properties of space-time covariance functions
- A likelihood ratio test for separability of covariances
- Test of Weak Separability for Spatially Stationary Functional Field
- Tests for separability in nonparametric covariance operators of random surfaces
- Alteration detection of tensor dependence structure via sparsity-exploited reranking algorithm
- Inference and Computation for Sparsely Sampled Random Surfaces
- Testing separability of functional time series
Uses Software
This page was built for publication: A test for separability in covariance operators of random surfaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215739)
