Stationary vine copula models for multivariate time series

被引:8
|
作者
Nagler, Thomas [1 ]
Krueger, Daniel [2 ]
Min, Aleksey [2 ]
机构
[1] Delft Univ Technol, Delft Inst Appl Math, Mekelweg 4, NL-2628 CD Delft, Netherlands
[2] Tech Univ Munich, Dept Math, Boltzmannstr 3, D-85748 Garching, Germany
关键词
Pair-copula; Dependence; Bootstrap; Forecasting; Markov chain; Sequential maximum likelihood; SEMIPARAMETRIC ESTIMATION; EFFICIENT ESTIMATION; DYNAMIC-MODELS; BOOTSTRAP; DEPENDENCE;
D O I
10.1016/j.jeconom.2021.11.015
中图分类号
F [经济];
学科分类号
02 ;
摘要
Multivariate time series exhibit two types of dependence: across variables and across time points. Vine copulas are graphical models for the dependence and can conveniently capture both types of dependence in the same model. We derive the maximal class of graph structures that guarantee stationarity under a natural and verifiable condition called translation invariance. We propose computationally efficient methods for estimation, simulation, prediction, and uncertainty quantification and show their validity by asymptotic results and simulations. The theoretical results allow for misspecified models and, even when specialized to the iid case, go beyond what is available in the literature. The new model class is illustrated by an application to forecasting returns of a portfolio of 20 stocks, where they show excellent forecast performance. The paper is accompanied by an open source software implementation. (C) 2022 The Author(s). Published by Elsevier B.V.
引用
收藏
页码:305 / 324
页数:20
相关论文
共 50 条