The (maximum) limit for shape is set on 10 for the function garchfit. Hence it is impossible to estimate data for a student-t distributed error term with a higher degrees of freedom than 10. I wonder how to change this parameter. I hope someone could give me the answer. Thank you verry much in advance! -- View this message in context: http://r.789695.n4.nabble.com/Fgarch-garchFit-limits-of-transformations-tp3947351p3947351.html Sent from the R help mailing list archive at Nabble.com.