[ADMB Users] PBSadmb - an R interface for ADMB

dave fournier otter at otter-rsch.com
Fri Nov 27 11:53:50 PST 2009


Jon,

A good example would be your  catch at age model
which I extended to R.

http://otter-rsch.ca/tresults.htm


(The Splus code had a few fatal errors BTW.)  It runs
about 1000 times faster than R, that is a few seconds vs over an hour.

Hans extended it to have random effects in the recruitment.
That version runs in about 2.5 minutes.

One can also extend that to a nonlinear REML by integrating over the
the parameters of the multinomial. Seems to work well not withstanding
Bates opining that such methods do not work for nonlinear RE models.
(I suppose they don't work when he does them.)


-- 
David A. Fournier
P.O. Box 2040,
Sidney, B.C. V8l 3S3
Canada
Phone/FAX 250-655-3364
http://otter-rsch.com



More information about the Users mailing list