[ADMB Users] "Hessian does not appear to be positive definite"

[dave fournier]

Hi,

I think there is a bit lost in translation here.

>I fixed the parameters and simulate Y to test the ADMB script. The
>retrieved
>parameters have exactly (and amazingly!) the same values as I fixed >(which
>is not the case when using optim function in R or fminsearch in matlab and
>it's much longer).

Do you mean the you used known parameters to simulate some data and then
fit the data and got the parameters back.  Is that the same data set
for which the results you posted here are from?  anyway if you send me
the tpl file and every thing needed to run the model I'll take a look at it.

     Dave


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