Testing separability of space--time functional processes

TL;DR

This paper introduces new statistical tests for assessing whether spatio-temporal functional data have a separable covariance structure, improving inference accuracy without relying on computationally intensive resampling methods.

Contribution

The paper develops three novel tests for separability in spatio-temporal data, including a functional extension of existing likelihood methods and two quadratic form-based tests, with a focus on the norm approach.

Findings

The norm approach outperforms other methods in finite sample scenarios.

The tests are based on asymptotic distributions of estimators, avoiding resampling.

Application to wind data demonstrates practical utility.

Abstract

We present a new methodology and accompanying theory to test for separability of spatio-temporal functional data. In spatio-temporal statistics, separability is a common simplifying assumption concerning the covariance structure which, if true, can greatly increase estimation accuracy and inferential power. While our focus is on testing for the separation of space and time in spatio-temporal data, our methods can be applied to any area where separability is useful, including biomedical imaging. We present three tests, one being a functional extension of the Monte Carlo likelihood method of Mitchell et. al. (2005), while the other two are based on quadratic forms. Our tests are based on asymptotic distributions of maximum likelihood estimators, and do not require Monte Carlo or bootstrap replications. The specification of the joint asymptotic distribution of these estimators is the main theoretical contribution of this paper. It can be used to derive many other tests. The main methodological finding is that one of the quadratic form methods, which we call a norm approach, emerges as a clear winner in terms of finite sample performance in nearly every setting we considered. The norm approach focuses directly on the Frobenius distance between the spatio-temporal covariance function and its separable approximation. We demonstrate the efficacy of our methods via simulations and an application to Irish wind data.