RATS 10.1
RATS 10.1

The HMATRICES option provides the covariance matrices as a SERIES of SYMMETRIC arrays. The MVHSERIES option gives them as a SYMMETRIC of SERIES. The latter is more convenient if you want to graph one of the components, or use it as an input to (for instance) a regression. The former is more useful for things like forecasting the variance, where you need to be able to work with the covariance matrix as a whole.

 

The following uses HMATRICES and the %CVTOCORR function to generate and graph the conditional correlations. %CVTOCORR transforms a covariance matrix to a correlation matrix, then the (1,2) etc. extracts a particular element from that.

 

Note that the process of extracting and analyzing the covariances or correlations is the same for all types of multivariate GARCH models.

 

garch(p=1,q=1,mv=dcc,variances=koutmos,hmatrices=hh) / $

   xjpn xfra xsui

 

set jpnfra = %cvtocorr(hh(t))(1,2)

set jpnsui = %cvtocorr(hh(t))(1,3)

set frasui = %cvtocorr(hh(t))(2,3)

 

spgraph(vfields=3,footer="Conditional Correlations")

 graph(header="Japan with France",min=-1.0,max=1.0)

 # jpnfra

 graph(header="Japan with Switzerland",min=-1.0,max=1.0)

 # jpnsui

 graph(header="France with Switzerland",min=-1.0,max=1.0)

 # frasui

spgraph(done)


Copyright © 2025 Thomas A. Doan