[ADMB Users] Problems with RE model, using FUNCTIONs for integration

H. Skaug hskaug at gmail.com
Fri Nov 30 11:32:36 PST 2012


Yes, I think that was the problem here. It is always a good idea to
add a small amount
to stay in the safe zone: log(1e-10 + x),...sqrt(1e-10 + x).

Hans

>
> Any explanation why this is?  Does having the base of the pow( )
> function equal to 0.0 mess up differentiability in some weird way?
>



More information about the Users mailing list