I have not included the previous postings because they came out very strangely on my mail
reader. However, the question concerned the choice of minimizer for the zeroinfl()
function, which apparently allows any of the current 6 methods of optim() for this
purpose. The original poster wanted to
John,
thanks for the comments, very useful.
Just three short additions specific to the ZINB case:
1. zeroinfl() doesn't uses BFGS (by default) and not Newton-Raphson
because we have analytical gradients but not an analytical Hessian.
2. If the default starting values do not work,
Regarding Newton-Raphson, I would add that there are certain kinds
of function for which the method *cannot* work.
N-R is essentially a root-finding technique, and when used for
finding a minimum (or maximum) it is applied to finding the root
of the deriviative.
As an example of a class of
3 matches
Mail list logo