Re: [Gretl-users] The local linear trend model estimation (Kalman filter)
On Thu, 15 Feb 2018, Henrique Andrade wrote:
Dear Gretl Community,
I'm trying to replicate the results from Commandeur & Koopman (2007)
(chapter 3, section 3.2, pp. 23-26) but I'm getting no success :-(
Please take a look at the code I'm running (the .inp file is
attached):
Convergence problems; try substituting the end of your script with the
following:
<hansl>
/* maximum likelihood estimation */
"stochastic KSI" <- mle ll = ERR ? NA : kalman.llt
kalman.obsvar = var_irreg^2
kalman.statevar[1, 1] = var_level^2
kalman.statevar[2, 2] = var_slope^2
ERR = kfilter(&kalman)
params var_irreg var_level var_slope
end mle --lbfgs --quiet
loop foreach i irreg level slope
printf "var_$i : %8.6f\n", var_$i^2
endloop
</hansl>
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------