R help - Jul 2005 - Correct variance for prediction intervals from nlme and gnls objects

Hello,
I am writing a set of functions to do prediction and calibration
intervals 
for at least the subset of selfstarting models if not some more general
ones.

I need to be able to extract the varFunction from a fit object
and evaluate it at a predicted point. Are there any examples around?

Also in a self start model, say SSlogis, how would I get the gradient
at a point?

Thanks
Nicholas

PS I am sure I will have more questions

On 7/19/05, Nicholas Lewin-Koh <nikko at hailmail.net>
wrote:
> Hello,
> I am writing a set of functions to do prediction and calibration
> intervals
> for at least the subset of selfstarting models if not some more general
> ones.
> 
> I need to be able to extract the varFunction from a fit object
> and evaluate it at a predicted point. Are there any examples around?
> 
> Also in a self start model, say SSlogis, how would I get the gradient
> at a point?
I think that the output of 

example(SSlogis)

should answer that question for you.

Hi,
Yes, I looked more carefully at the code and realized the parameters
have to be named
and then the gradient is returned so that
SSlogis(3.4,4,5,6) does not return the gradient as an attribute but
Asym<-4
xmid<-5
scal<-6
SSlogis(3.4,Asym,xmid,scal)

does.

However what I am finding more vexing is if I fit a model, say

fit<-gnls(resp~SSlogis(covar,Asym,xmid,scal), data=foo,
weights=varPower())

and I want to evaluate the arbitrary variance function at a new x, x0
then how do i get the variance function from the fit object and evaluate
it
at f(x0,..)?

So far I can predict at x0 using predict(fit, newdata=list(covar=x0)) to
get the fitted value
but how to I plug that in to the varStruct stored in fit$modelStruct?

Thanks
Nicholas
On Tue, 19 Jul 2005 11:48:18 -0500, "Douglas Bates" <dmbates at
gmail.com>
said:
> On 7/19/05, Nicholas Lewin-Koh <nikko at hailmail.net> wrote:
> > Hello,
> > I am writing a set of functions to do prediction and calibration
> > intervals
> > for at least the subset of selfstarting models if not some more
general
> > ones.
> > 
> > I need to be able to extract the varFunction from a fit object
> > and evaluate it at a predicted point. Are there any examples around?
> > 
> > Also in a self start model, say SSlogis, how would I get the gradient
> > at a point?
> 
> I think that the output of 
> 
> example(SSlogis)
> 
> should answer that question for you.