Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/205303 
Year of Publication: 
2019
Series/Report no.: 
Tinbergen Institute Discussion Paper No. TI 2019-013/IV
Publisher: 
Tinbergen Institute, Amsterdam and Rotterdam
Abstract: 
We develop new multi-factor dynamic copula models with time-varying factor loadings and observation-driven dynamics. The new models are highly flexible, scalable to high dimensions, and ensure positivity of covariance and correlation matrices. A closed-form likelihood expression allows for straightforward parameter estimation and likelihood in- ference. We apply the new model to a large panel of 100 U.S. stocks over the period 2001Ð2014. The proposed multi-factor structure is much better than existing (single- factor) models at describing stock return dependence dynamics in high-dimensions. The new factor models also improve one-step-ahead copula density forecasts and global min- imum variance portfolio performance. Finally, we investigate different mechanisms to allocate firms into groups and find that a simple industry classification outperforms al- ternatives based on observable risk factors, such as size, value or momentum.
Subjects: 
factor copulas
factor structure
score-driven dynamics
multivariate density forecast
JEL: 
C32
C58
G17
Document Type: 
Working Paper

Files in This Item:
File
Size
1.11 MB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.