[R-SIG-Finance] seasonality in rugarch

[aschmid1]

Hi,
I'm working with a sample that has a strong weekly seasonality and 
wonder if rugarch can handle a multiplicative ARIMA(p,d,q)P,D,Q)s. I 
tried additive seasonal model for which I simply put 51 dummy variables 
as external regressors into the mean but, alas, the model does not 
converge (rugarch-->warning: failed to invert hessian) with or without 
dummies.
Here is my script:

spec1111 = ugarchspec(variance.model = list(model = "sGARCH", garchOrder 
= c(1,1)), mean.model = list(armaOrder = c(1,1), include.mean = T, 
external.regressors = X), distribution.model = "sged")

fit1111<-ugarchfit(data=inp[,2], spec=spec1111, solver = "hybrid", 
solver.control = list(trace = TRUE, tol=1e-4, delta=1e-6))


Thanks! Alec