[R] Simulating a VEC

Laura Catalina Echeverri lauracatalina at gmail.com
Thu Nov 22 18:37:53 CET 2012


Hello everyone,

I have estimated a VEC using functions of package urca. Now I need to
simulate several trajectories of the variables of the model based in the
information of the model. To do that first I converted the VEC to a VAR
using vec2var (from package vars) and then I converted de VAR to an ARMA
using ARMA function of package dse. The idea is to use the function simulate
(from package dse), to simulate the ARMA from the VEC using the initial
values of the variables of the model, the exogenous variables in the
simulation period and the matrix of covariances of the residuals of the VEC
model, to model the residuals in each simulation. Then I made several
iterations of this simulation, to obtain different trajectories and conclude
about the model; but sometimes the plot of the simulations shows values of
the variables on the order of +-1e137 (a really big number) and I don't know
why it is happening. Does anyone of you know what can be happening?

Thanks in advance,

Laura Echeverri 



--
View this message in context: http://r.789695.n4.nabble.com/Simulating-a-VEC-tp4650463.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list