DCC- and DECO-HEAVY: Multivariate GARCH models based on realized variances and correlations
(2023) International Journal of Forecasting — Vol. 39, n° 2, p. 938-955 (2023)
Files
CORE_RP_3345.pdf
Open Access - Adobe PDF
- 1.59 MB
Details
- Authors
Bauwens, Luc 
- Abstract
- This paper introduces the scalar DCC-HEAVY and DECO-HEAVY models for conditional variances and correlations of daily returns based on measures of realized variances and correlations built from intraday data. Formulas for multi-step forecasts of conditional variances and correlations are provided. Asymmetric versions of the models are developed. An empirical study shows that in terms of forecasts the scalar HEAVY models outperform the scalar BEKK-HEAVY model based on realized covariances and the scalar BEKK, DCC, and DECO multivariate GARCH models based exclusively on daily data.
- Affiliations
Citations
Bauwens, L., & Xu, Y. (2023). DCC- and DECO-HEAVY: Multivariate GARCH models based on realized variances and correlations. International Journal of Forecasting, 39(2), 938-955. https://doi.org/10.1016/j.ijforecast.2022.03.005 (Original work published 2023)