You should probably try to find some literature on GARCH models with seasonal data. The problem is that the actual "variance" in the seasonal series is primarily (overwhelmingly?) in the seasonal. Both seasonal dummies and seasonal differencing largely eliminates most of that. You *can* put seasonal dummies in the variance equations---something like that is sometimes done with day-of-week effects in financial returns. I don't know whether that will help with your analysis.melkania wrote:Hi Tom,
I figured that the annual returns are a AR(1) process, and so your previous advice makes complete sense. So please ignore my first question.
Could you please share any suggestions on the second question: dealing with a pair of variables when seasonality is high in one but not in another?
Thanks!