Join GitHub today
GitHub is home to over 36 million developers working together to host and review code, manage projects, and build software together.Sign up
REF/ENH: LikelihoodModel.fit optimization, make hessian optional #1943
We need a fit keyword to turn of the hessian calculation if it is not needed.
see #1940 (comment)
Another possible case:
example: NegativeBinomial I don't see how this works, or why it works:
So the hessian should be for the transformed parameterization?
temporary bug and prio-high label, until this is checked.
maybe my reading is wrong, maybe there's a bug
check unit tests:
which means default
This was referenced
Aug 31, 2014
referenced this issue
Sep 18, 2014
NegativeBinomial doesn't have a bug.
the Hessian evaluates the derivative at the transformed value, but it is the derivative wrt. the untransformed parameter. AFAICS
But then, why did I run into problems when I added the robust covariances and cov_type?
OK, to answer the last part: score is the derivative with respect to the transformed params, but not the hessian.
NegativeBinomial is fine except for inconsistent definition of score and hessian wrt transparams.