Time series with infinite-order partial copula dependence

Alexander John McNeil; Martin Bladt

doi:10.1515/demo-2022-0105

Time series with infinite-order partial copula dependence

Alexander John McNeil, Martin Bladt

The York Management School

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

Abstract

Stationary and ergodic time series can be constructed using an s-vine decomposition based on sets of bivariate copula functions. The extension of such processes to infinite copula sequences is considered and shown to yield a rich class of models that generalizes Gaussian ARMA and ARFIMA processes to allow both non-Gaussian marginal behaviour and a non-Gaussian description of the serial partial dependence structure. Extensions of classical causal and invertible representations of linear processes to general s-vine processes are proposed and investigated. A practical and parsimonious method for parameterizing s-vine processes using the Kendall partial autocorrelation function is developed. The potential of the resulting models to give improved statistical fits in many applications is indicated with an example using macroeconomic data.

Original language	English
Pages (from-to)	87–107
Journal	Dependence Modeling
Volume	10
DOIs	https://doi.org/10.1515/demo-2022-0105
Publication status	Published - 23 May 2022

Access to Document

10.1515/demo-2022-0105Licence: CC BY

s_vine_processes_01042022Accepted author manuscript, 634 KB

Cite this

@article{3cc482e002654a48a4dd93915735849b,

title = "Time series with infinite-order partial copula dependence",

abstract = "Stationary and ergodic time series can be constructed using an s-vine decomposition based on sets of bivariate copula functions. The extension of such processes to infinite copula sequences is considered and shown to yield a rich class of models that generalizes Gaussian ARMA and ARFIMA processes to allow both non-Gaussian marginal behaviour and a non-Gaussian description of the serial partial dependence structure. Extensions of classical causal and invertible representations of linear processes to general s-vine processes are proposed and investigated. A practical and parsimonious method for parameterizing s-vine processes using the Kendall partial autocorrelation function is developed. The potential of the resulting models to give improved statistical fits in many applications is indicated with an example using macroeconomic data.",

author = "McNeil, {Alexander John} and Martin Bladt",

year = "2022",

month = may,

day = "23",

doi = "10.1515/demo-2022-0105",

language = "English",

volume = "10",

pages = "87–107",

journal = "Dependence Modeling",

issn = "2300-2298",

publisher = "De Gruyter",

}

TY - JOUR

T1 - Time series with infinite-order partial copula dependence

AU - McNeil, Alexander John

AU - Bladt, Martin

PY - 2022/5/23

Y1 - 2022/5/23

N2 - Stationary and ergodic time series can be constructed using an s-vine decomposition based on sets of bivariate copula functions. The extension of such processes to infinite copula sequences is considered and shown to yield a rich class of models that generalizes Gaussian ARMA and ARFIMA processes to allow both non-Gaussian marginal behaviour and a non-Gaussian description of the serial partial dependence structure. Extensions of classical causal and invertible representations of linear processes to general s-vine processes are proposed and investigated. A practical and parsimonious method for parameterizing s-vine processes using the Kendall partial autocorrelation function is developed. The potential of the resulting models to give improved statistical fits in many applications is indicated with an example using macroeconomic data.

AB - Stationary and ergodic time series can be constructed using an s-vine decomposition based on sets of bivariate copula functions. The extension of such processes to infinite copula sequences is considered and shown to yield a rich class of models that generalizes Gaussian ARMA and ARFIMA processes to allow both non-Gaussian marginal behaviour and a non-Gaussian description of the serial partial dependence structure. Extensions of classical causal and invertible representations of linear processes to general s-vine processes are proposed and investigated. A practical and parsimonious method for parameterizing s-vine processes using the Kendall partial autocorrelation function is developed. The potential of the resulting models to give improved statistical fits in many applications is indicated with an example using macroeconomic data.

U2 - 10.1515/demo-2022-0105

DO - 10.1515/demo-2022-0105

M3 - Article

SN - 2300-2298

VL - 10

SP - 87

EP - 107

JO - Dependence Modeling

JF - Dependence Modeling

ER -