Page 1 of 1

Null hypothesis related to estimated degrees of freedom

Posted: Sun Mar 30, 2014 9:02 am
by strypste
Hi there

EViews estimates the degrees of freedom automatically when one estimates a garch model with the t distribution as error distribution. If the degrees of freedom is large, then this does not give much evidence for the t distribution. But what is the null hypothesis in terms of the model for the estimated degrees of freedom?

Cheers
strypste