hello everybody, I would like to fit a model to a times series (testing set) for out of sample predictions using garchFit(). I would like to keep the coefficients of ARMA/GARCH model fixed (as found by fitting the model to my training set). The arima fitting function has such an option for that (fixed=NULL) but the garchFit() doesnt. It is very important for me to keep the same coefficients for my testing set as for my training set (where the model is found) in order to make out of sample predictions for a new set ( testing set) using the same model found for my training set. So basically what I would like is to fit an ARMA-GARCH model but with predetermined coefficients. If you have any ideas please share them with me...I will be very grateful. Thanks, G -- View this message in context: http://r.789695.n4.nabble.com/fGarch-garchFit-with-fixed-coefficents-tp2289304p2289304.html Sent from the R help mailing list archive at Nabble.com.