Is there anyway to get the theoretical third central moment? I am running an exact model and then estimate it.
A simple minded way if doing this is to glean the smoothed series from oo file and manually compute it. Is it reasonable to do it?
We are working on supporting theoretical third moments, but are not there yet. Looking at the smoothed series would not help, because they are data dependent and not a theoretical property of the model. The only thing you can do is simulate a really long time series from the model and then look at the reported skewness in oo_.skewness