Re: [S] Var-Covar Matrices of non-linear parameters

Pedro de Barros (
Mon, 15 Jun 1998 12:02:47 +0100

Dear Prof. Ripley,
I am trying to use vcov.nlregb, from whithin a function, but there must be
something wrong, as I always get an error message saying
- Error in vcov.nlregb(object = Fit2, method = "Fisher"..: Object "Fit2" not

However, I print "Fit2" from whithin the same function, and I get a correct
printing, so the object is there.
Do you have any clue as to what could be the problem?
I am using S-Plus 4, release 3, under Windows NT.

I appreciate any help.
Best regards,

At 08:47 AM 6/14/98 +0100, you wrote:
>On Thu, 11 Jun 1998, Pedro de Barros wrote:
>> Dear all,
>> I am trying to find a way of obtaining the variance-covariance matrix for
>> the estimated parameters when running nlregb(), nls() or nlminb(),
>> equivalent to the "var" component of a glim() fit. (I want a simple way of
>> estimating confidence limits for the parameters).
>> Does anyone have a tip on how to do this, or code he/she would be willing to
>> share?
>For nlregb and nls, see the vcov function in the MASS library. The
>question is not defined for nlminb: it depends on what you are
>minimizing (a deviance, minus log-likelihood, minus likelihood?)
>Brian D. Ripley,
>Professor of Applied Statistics,
>University of Oxford, Tel: +44 1865 272861 (self)
>1 South Parks Road, +44 1865 272860 (secr)
>Oxford OX1 3TG, UK Fax: +44 1865 272595
Pedro de Barros Tel: +351 89 800918/900/100
Universidade do Algarve Fax: +351 89 818353
Unidade de Ciencias e Tecnologias dos Recursos Aquáticos E-mail:
Campus de Gambelas, 8000 FARO, PORTUGAL

This message was distributed by To unsubscribe
send e-mail to with the BODY of the
message: unsubscribe s-news