i used the automatic arima forecast to determine the order of AR in my series in order to put an equation into a garch model.
i am testing the day of the week effect and using 'p' lagged variables, do i also need to include the MA terms?
also, i am testing over different periods, do i need to do a separate arima forecast for returns on each period? or will the AR figure that i get when forecasting over the entire period be fine?
For econometric discussions not necessarily related to EViews.
1 post • Page 1 of 1
Who is online
Users browsing this forum: No registered users and 4 guests