Re: [Gretl-users] Estimating ARMA model with GARCH errors
On Thu, June 8, 2006 03:45, sudip mukherjee wrote:
Hi,
I want to know how can I estimate the parameters of an
ARMA(1,1) model with Garch(1,1) errors. I believe all
the parameters will need to be estimate
simultaneously.
at present, the only way you have in gretl to estimate an arma model with
garch variance is to use the "mle" command. Section 10.4 in the manual reports
an example with a garch(1,1) model. A simple adaptation of that example
follows:
open djclose
series y = 100*ldiff(djclose)
scalar mu = 0.0
scalar omega = 1
scalar alpha = 0.4
scalar beta = 0.0
scalar phi = 0.0
scalar theta = 0.0
mle ll = -0.5*(log(h) + (e^2)/h)
series e = 0
series e = y - mu - phi*y(-1) - theta*e(-1)
series h = var(y)
series h = omega + alpha*(e(-1))^2 + beta*h(-1)
params mu phi theta omega alpha beta
end mle
Clearly, this is going to "feel" slower than a builtin command, but it should
get the job done.
Riccardo "Jack" Lucchetti
Dipartimento di Economia
Facoltà di Economia "G. Fuà"
Ancona