[ADMB Users] difference between ADMB-RE and R/mgcv in SEs for smoother coefficients in a GAM fitted by maximum likelihood

dave fournier davef at otter-rsch.com
Thu Nov 29 13:53:45 PST 2012

OK that helped.  Around line 72 in getbigs.cpp I beleive the sign is wrong.
It should be


This corresponds to   uhat'(x) = - (L_uu)^{-1} L_xu

More information about the Users mailing list