Template-Type: ReDIF-Paper 1.0
Author-Name: Luc Bauwens
Author-Name-First: Luc
Author-Name-Last: Bawens
Author-Email: luc.bauwens@uclouvain.be
Author-Workplace-Name: Universite Côte d'Azur, SKEMA, France.
Author-Name: Manuela Braione
Author-Name-First: Manuela
Author-Name-Last: Braione
Author-Email: manuela.braione@uclouvain.be
Author-Workplace-Name: Universite Catholique de Louvain,CORE, B-1348 Louvain-La-Neuve, Belgium.
Author-Name: Giuseppe Storti
Author-Name-First: Giuseppe
Author-Name-Last: Storti
Author-Email: storti@unisa.it
Author-Workplace-Name: Dipartimento di Scienze Economiche e Statistiche (DISES), Università degli Studi di Salerno
Title: A Dynamic Component Model for Forecasting High-Dimensional Realized Covariances Matrices
Abstract:  The Multiplicative MIDAS Realized DCC (MMReDCC) model simultaneously accounts for short and long term dynamics in the conditional (co)volatilities of asset returns, in line with the empirical evidence suggesting that their level is changing over time as a function of economic conditions. Herein the applicability of the model is improved along two directions. First, by proposing an algorithm that relies on the maximization of an iteratively re-computed moment-based pro_le likelihood function and keeps estimation feasible in large dimensions by mitigating the incidental parameter problem. Second, by illustrating a conditional bootstrap procedure to generate multi-step ahead predictions from the model. In an empirical application on a dataset of forty-six equities, the MMReDCC model is found to statistically outperform the selected benchmarks in terms of in-sample _t as well as in terms of out-of-sample covariance predictions. The latter are mostly significant in periods of high market volatility.
Length: 31 pages
Creation-Date:2020-07
Revision-Date:2020-07
Publication-Status: Published in Working Papers, September 2016, pages 1-31.
File-URL:https://www.dises.unisa.it/RePEc/sep/wpaper/3_234.pdf
File-Format:Application/pdf
File-Function:First version, 2016
Number:3_234
Classification-JEL:
Keywords: Realized covariance, dynamic component models, multi-step forecasting, iterative algorithm
Handle:RePEc:sep:wpaper:3_234