Distance covariance for discretized stochastic processes

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Distance covariance for discretized stochastic processes. / Dehling, Herold G.; Matsui, Muneya ; Mikosch, Thomas Valentin; Samorodnitsky, Gennady; Tafakori, Laleh .

I: Bernoulli, Bind 26, 2020, s. 2758-2789.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Dehling, HG, Matsui, M, Mikosch, TV, Samorodnitsky, G & Tafakori, L 2020, 'Distance covariance for discretized stochastic processes', Bernoulli, bind 26, s. 2758-2789. https://doi.org/10.3150/20-BEJ1206

APA

Dehling, H. G., Matsui, M., Mikosch, T. V., Samorodnitsky, G., & Tafakori, L. (2020). Distance covariance for discretized stochastic processes. Bernoulli, 26, 2758-2789. https://doi.org/10.3150/20-BEJ1206

Vancouver

Dehling HG, Matsui M, Mikosch TV, Samorodnitsky G, Tafakori L. Distance covariance for discretized stochastic processes. Bernoulli. 2020;26:2758-2789. https://doi.org/10.3150/20-BEJ1206

Author

Dehling, Herold G. ; Matsui, Muneya ; Mikosch, Thomas Valentin ; Samorodnitsky, Gennady ; Tafakori, Laleh . / Distance covariance for discretized stochastic processes. I: Bernoulli. 2020 ; Bind 26. s. 2758-2789.

Bibtex

@article{4004d306937d432a9c33153191f06440,
title = "Distance covariance for discretized stochastic processes",
abstract = "Given an i.i.d. sequence of pairs of stochastic processes on the unit interval we construct a measure of independence for the components of the pairs. We define distance covariance and distance correlation based on approximations of the component processes at finitely many discretization points. Assuming that the mesh of the discretization converges to zero as a suitable function of the sample size, we show that the sample distance covariance and correlation converge to limits which are zero if and only if the component processes are independent. To construct a test for independence of the discretized component processes, we show consistency of the bootstrap for the corresponding sample distance covariance/correlation.",
author = "Dehling, {Herold G.} and Muneya Matsui and Mikosch, {Thomas Valentin} and Gennady Samorodnitsky and Laleh Tafakori",
year = "2020",
doi = "10.3150/20-BEJ1206",
language = "English",
volume = "26",
pages = "2758--2789",
journal = "Bernoulli",
issn = "1350-7265",
publisher = "International Statistical Institute",

}

RIS

TY - JOUR

T1 - Distance covariance for discretized stochastic processes

AU - Dehling, Herold G.

AU - Matsui, Muneya

AU - Mikosch, Thomas Valentin

AU - Samorodnitsky, Gennady

AU - Tafakori, Laleh

PY - 2020

Y1 - 2020

N2 - Given an i.i.d. sequence of pairs of stochastic processes on the unit interval we construct a measure of independence for the components of the pairs. We define distance covariance and distance correlation based on approximations of the component processes at finitely many discretization points. Assuming that the mesh of the discretization converges to zero as a suitable function of the sample size, we show that the sample distance covariance and correlation converge to limits which are zero if and only if the component processes are independent. To construct a test for independence of the discretized component processes, we show consistency of the bootstrap for the corresponding sample distance covariance/correlation.

AB - Given an i.i.d. sequence of pairs of stochastic processes on the unit interval we construct a measure of independence for the components of the pairs. We define distance covariance and distance correlation based on approximations of the component processes at finitely many discretization points. Assuming that the mesh of the discretization converges to zero as a suitable function of the sample size, we show that the sample distance covariance and correlation converge to limits which are zero if and only if the component processes are independent. To construct a test for independence of the discretized component processes, we show consistency of the bootstrap for the corresponding sample distance covariance/correlation.

U2 - 10.3150/20-BEJ1206

DO - 10.3150/20-BEJ1206

M3 - Journal article

VL - 26

SP - 2758

EP - 2789

JO - Bernoulli

JF - Bernoulli

SN - 1350-7265

ER -

ID: 248031539