FitMultivariateGarch: Estimation of multivariate GARCH models

In R-Finance/Meucci: Collection of functionality ported from the MATLAB code of Attilio Meucci.

Description

Estimation of multivariate GARCH models

Usage

  FitMultivariateGarch(returns, demean = 1, eps = 0,
    df = 500)

Arguments

returns	: [matrix] (T x N) returns so rows must correspond to time and columns to assets
demean	: [scalar] specifies whether returns should be demeaned (if demean = 1) or not to estimate the model; default value is 1.
eps	: [scalar] used in enforcing a_ii + b_ii <= 1 - eps; the default value is zero
df	: [scalar] degree of freedom for the t-distribution; the default value is 500 to make it, basically, normal

Value

mu : [vector]

ATMF : [matrix] coefficient matrix A-tilde (in the notation of the paper)

BTMF : [matrix] coefficient matrix B-tilde (in the notation of the paper)

CTMF : [matrix] coefficient matrix C-tilde (in the notation of the paper)

Hhat : [matrix] forecasted conditional covariance matrix

Note

Code for MATLAB initially written by Olivier Ledoit and Michael Wolf

Author(s)

Xavier Valls [e-mail]

References

A. Meucci - "Exercises in Advanced Risk and Portfolio Management" http://symmys.com/node/170, "E 136 - Equity market: multivariate GARCH process".

See Meucci's script for "FitMultivariateGarch.m"

R-Finance/Meucci documentation built on May 8, 2019, 3:52 a.m.