Distance covariance for random fields

DOI10.1016/J.SPA.2022.04.009zbMATH Open1493.62069arXiv2107.03162OpenAlexW3179077179MaRDI QIDQ2145778FDOQ2145778

Laleh Tafakori, T. Mikosch, Muneya Matsui, Rasool Roozegar

Publication date: 20 June 2022

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: We study an independence test based on distance correlation for random fields $(X,Y)$. We consider the situations when $(X,Y)$ is observed on a lattice with equidistant grid sizes and when $(X,Y)$ is observed at random locations. We provide asymptotic theory for the sample distance correlation in both situations and show bootstrap consistency. The latter fact allows one to build a test for independence of $X$ and $Y$ based on the considered discretizations of these fields. We illustrate the performance of the bootstrap test in a simulation study involving fractional Brownian and infinite variance stable fields. The independence test is applied to Japanese meteorological data, which are observed over the entire area of Japan.

Full work available at URL: https://arxiv.org/abs/2107.03162

Recommendations

• Measuring and testing dependence by correlation of distances
• Distance covariance for discretized stochastic processes
• The affinely invariant distance correlation
• Distance covariance for stochastic processes
• A distance-based test of independence between two multivariate time series

zbMATH Keywords

distance covarianceindependence testrandom fieldempirical characteristic function

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Random fields; image analysis (62M40) Asymptotic distribution theory in statistics (62E20) Central limit and other weak theorems (60F05) (L^p)-limit theorems (60F25)

Cites Work

• Measuring and testing dependence by correlation of distances
• Approximation Theorems of Mathematical Statistics
• Partial distance correlation with methods for dissimilarities
• Distance covariance in metric spaces
• On the bootstrap of \(U\) and \(V\) statistics
• Measuring nonlinear dependence in time-series, a distance correlation approach
• Title not available (Why is that?)
• The distance correlation \(t\)-test of independence in high dimension
• Title not available (Why is that?)
• A Consistent Test for Bivariate Dependence
• Brownian distance covariance
• Title not available (Why is that?)
• Testing Mutual Independence in High Dimension via Distance Covariance
• Asymptotic properties and Hausdorff dimensions of fractional Brownian sheets
• Title not available (Why is that?)
• Random quadratic forms and the bootstrap for \(U\)-statistics
• Sample function properties of multi-parameter stable processes
• Title not available (Why is that?)
• Testing multivariate uniformity: The distance‐to‐boundary method
• Title not available (Why is that?)
• A multivariate uniformity test for the case of unknown support
• Testing independence for multivariate time series via the auto-distance correlation matrix
• Testing multivariate uniformity based on random geometric graphs
• Applications of distance correlation to time series
• Distance-based and RKHS-based dependence metrics in high dimension
• Distance covariance for discretized stochastic processes
• Distance covariance for stochastic processes
• Asymptotic distributions of high-dimensional distance correlation inference
• Fourier-type tests of mutual independence between functional time series
• Testing serial independence with functional data
• Testing independence between two spatial random fields
• Title not available (Why is that?)

Cited In (3)

• Generalization of the HSIC and distance covariance using PDI kernels
• A basic treatment of the distance covariance
• Distance covariance for discretized stochastic processes

This page was built for publication: Distance covariance for random fields

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2145778)