Template-Type: ReDIF-Paper 1.0

Author-Name: Roland Weigand
Author-X-Name-First: Roland 
Author-X-Name-Last: Weigand

Title: Matrix Box-Cox Models for Multivariate Realized Volatility

	
Abstract: We propose exible models for multivariate realized volatility dynamics which involve generalizations of the Box-Cox transform to the matrix case. The matrix Box-Cox model of realized covariances (MBC-RCov) is based on transformations of the covariance matrix eigenvalues, while for the Box-Cox dynamic correlation (BC-DC) specification the variances are transformed individually and modeled jointly with the correlations. We estimate transformation parameters by a new multivariate semiparametric estimator and discuss bias-corrected point and density forecasting by simulation. The methods are applied to stock market data where excellent in-sample and out-of-sample performance is found.
Length:  40 pages
Creation-Date:  2014-03
File-URL: http://www.bgpe.de/texte/DP/144_Weigand.pdf
File-Format: Application/pdf
File-Function: First version, 2014
Number: 144
Classification-JEL: C14, C32, C51, C53, C58
Keywords: realized covariance matrix, dynamic correlation, semiparametric estimation, density forecasting
Handle: RePEc:bav:wpaper:144_Weigand