Standard

Generalized information matrix tests for copulas. / Prokhorov, Artem; Schepsmeier, Ulf; Zhu, Yajing.

In: Econometric Reviews, Vol. 38, No. 9, 21.10.2019, p. 1024-1054.

Research output: Contribution to journal › Article › peer-review

Harvard

Prokhorov, A, Schepsmeier, U & Zhu, Y 2019, 'Generalized information matrix tests for copulas', Econometric Reviews, vol. 38, no. 9, pp. 1024-1054. https://doi.org/10.1080/07474938.2018.1514023

APA

Prokhorov, A., Schepsmeier, U., & Zhu, Y. (2019). Generalized information matrix tests for copulas. Econometric Reviews, 38(9), 1024-1054. https://doi.org/10.1080/07474938.2018.1514023

Vancouver

Prokhorov A, Schepsmeier U, Zhu Y. Generalized information matrix tests for copulas. Econometric Reviews. 2019 Oct 21;38(9):1024-1054. https://doi.org/10.1080/07474938.2018.1514023

Author

Prokhorov, Artem ; Schepsmeier, Ulf ; Zhu, Yajing. / Generalized information matrix tests for copulas. In: Econometric Reviews. 2019 ; Vol. 38, No. 9. pp. 1024-1054.

BibTeX

@article{424a4a588e30477ba73761f61d23f55c,
title = "Generalized information matrix tests for copulas",
abstract = "We propose a family of goodness-of-fit tests for copulas. The tests use generalizations of the information matrix (IM) equality of White and so relate to the copula test proposed by Huang and Prokhorov. The idea is that eigenspectrum-based statements of the IM equality reduce the degrees of freedom of the test{\textquoteright}s asymptotic distribution and lead to better size-power properties, even in high dimensions. The gains are especially pronounced for vine copulas, where additional benefits come from simplifications of score functions and the Hessian. We derive the asymptotic distribution of the generalized tests, accounting for the nonparametric estimation of the marginals and apply a parametric bootstrap procedure, valid when asymptotic critical values are inaccurate. In Monte Carlo simulations, we study the behavior of the new tests, compare them with several Cramer–von Mises type tests and confirm the desired properties of the new tests in high dimensions.",
keywords = "copula, goodness-of-fit, Information matrix equality, R-vines, vine copulas, SEMIPARAMETRIC ESTIMATION, VINES, OF-FIT TESTS, MODEL, INFERENCE, HIGH DIMENSIONS, DEPENDENCE",
author = "Artem Prokhorov and Ulf Schepsmeier and Yajing Zhu",
year = "2019",
month = oct,
day = "21",
doi = "10.1080/07474938.2018.1514023",
language = "English",
volume = "38",
pages = "1024--1054",
journal = "Econometric Reviews",
issn = "0747-4938",
publisher = "Taylor & Francis",
number = "9",

}

RIS

TY - JOUR

T1 - Generalized information matrix tests for copulas

AU - Prokhorov, Artem

AU - Schepsmeier, Ulf

AU - Zhu, Yajing

PY - 2019/10/21

Y1 - 2019/10/21

N2 - We propose a family of goodness-of-fit tests for copulas. The tests use generalizations of the information matrix (IM) equality of White and so relate to the copula test proposed by Huang and Prokhorov. The idea is that eigenspectrum-based statements of the IM equality reduce the degrees of freedom of the test’s asymptotic distribution and lead to better size-power properties, even in high dimensions. The gains are especially pronounced for vine copulas, where additional benefits come from simplifications of score functions and the Hessian. We derive the asymptotic distribution of the generalized tests, accounting for the nonparametric estimation of the marginals and apply a parametric bootstrap procedure, valid when asymptotic critical values are inaccurate. In Monte Carlo simulations, we study the behavior of the new tests, compare them with several Cramer–von Mises type tests and confirm the desired properties of the new tests in high dimensions.

AB - We propose a family of goodness-of-fit tests for copulas. The tests use generalizations of the information matrix (IM) equality of White and so relate to the copula test proposed by Huang and Prokhorov. The idea is that eigenspectrum-based statements of the IM equality reduce the degrees of freedom of the test’s asymptotic distribution and lead to better size-power properties, even in high dimensions. The gains are especially pronounced for vine copulas, where additional benefits come from simplifications of score functions and the Hessian. We derive the asymptotic distribution of the generalized tests, accounting for the nonparametric estimation of the marginals and apply a parametric bootstrap procedure, valid when asymptotic critical values are inaccurate. In Monte Carlo simulations, we study the behavior of the new tests, compare them with several Cramer–von Mises type tests and confirm the desired properties of the new tests in high dimensions.

KW - copula

KW - goodness-of-fit

KW - Information matrix equality

KW - R-vines

KW - vine copulas

KW - SEMIPARAMETRIC ESTIMATION

KW - VINES

KW - OF-FIT TESTS

KW - MODEL

KW - INFERENCE

KW - HIGH DIMENSIONS

KW - DEPENDENCE

UR - http://www.scopus.com/inward/record.url?scp=85060331155&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/generalized-information-matrix-tests-copulas

U2 - 10.1080/07474938.2018.1514023

DO - 10.1080/07474938.2018.1514023

M3 - Article

AN - SCOPUS:85060331155

VL - 38

SP - 1024

EP - 1054

JO - Econometric Reviews

JF - Econometric Reviews

SN - 0747-4938

IS - 9

ER -

ID: 39428143