I haven't seen any replies to this post, so I will offer a couple
of comments.
First, your example is entirely too complicated and not self
contained for me to say much in the limited time I have for this. I
suggest you start by splitting your problem into several steps. For
Spencer,
Thank you for taking time to reply and offer suggestions. garchFit does
not allow 'formula.mean=~z+arma(p, q)', nor does it allow xreg=(x,y)
options. Any thing is xreg is ignored with a warming or error.
I have debugged garchFit and I know where the code should be modified to
I could use some help understanding how nls parses the formula argument
to a model.frame and estimates the model. I am trying to utilize the
functionality of the nls formula argument to modify garchFit() to handle
other variables in the mean equation besides just an arma(u,v)
specification.
My
