Hi,
Did you find a solution for your problem? I am also trying to implement
GARCH-MIDAS model and i have the same errors. I thing that is because of
constraints. I thing that during the optimisation process, parameters go out
to feasible region; and lead to a negative conditional variance. I tried
with constrOptim() function (i fixed constraint for paramerter); i did not
have warnings anymore. But the estimated parameters change a lot with the
initials values.
(i am a native french speaker;) )
--
View this message in context: http://r.789695.n4.nabble.com/simple-GARCH-model-tp4689179p4694664.html
Sent from the Rmetrics mailing list archive at Nabble.com.