nlme problems

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

nlme problems

Ken Beath
I'm maximising a reasonably complex function using nlme (version  
3.1-65, have also tried 3.1-66) and am having trouble with fixed  
parameter estimates slightly away from the maximum of the log  
likelihood. I have profiled the log likelihood and it is a parabola  
but with sum dips. Interestingly changing the parameterisation moves  
the dips around slightly. Unfortunately the PNLS step is finding a  
maximum at the dips rather than the mle. I have tried using starting  
values for the fixed parameters without change. Any ideas ?

Ken

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: nlme problems

Dieter Menne
Ken Beath <kbeath <at> efs.mq.edu.au> writes:

>
> I'm maximising a reasonably complex function using nlme (version  
> 3.1-65, have also tried 3.1-66) and am having trouble with fixed  
> parameter estimates slightly away from the maximum of the log  
> likelihood. I have profiled the log likelihood and it is a parabola  
> but with sum dips. Interestingly changing the parameterisation moves  
> the dips around slightly. Unfortunately the PNLS step is finding a  
> maximum at the dips rather than the mle. I have tried using starting  
> values for the fixed parameters without change. Any ideas ?

Ken,

you should not use nlme for "maximising a complex function", because it's a
rather specialized tool for mixed-model statistical analysis. Try to use optim
directly, which has quite a few methods to choose from, and one of them might
work for your problem.

Dieter

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: nlme problems

Ken Beath
In reply to this post by Ken Beath
I meant fitting not maximising, it is a nonlinear mixed effects  
model, with both fixed and random effects. My assumption is that for  
the function I am using the approximation approach used in nlme is  
not quite close enough, and nothing much that I can do, except for  
looking at starting values. I was hoping that someone would have  
other suggestions, so I will keep attempting to understand the  
control parameters.  I can add an extra parameter to the model and  
obtain a worse fit.

Ken

Dieter Menne writes:

>
>>
>> I'm maximising a reasonably complex function using nlme (version
>> 3.1-65, have also tried 3.1-66) and am having trouble with fixed
>> parameter estimates slightly away from the maximum of the log
>> likelihood. I have profiled the log likelihood and it is a parabola
>> but with sum dips. Interestingly changing the parameterisation moves
>> the dips around slightly. Unfortunately the PNLS step is finding a
>> maximum at the dips rather than the mle. I have tried using starting
>> values for the fixed parameters without change. Any ideas ?
>
> Ken,
>
> you should not use nlme for "maximising a complex function",  
> because it's a
> rather specialized tool for mixed-model statistical analysis. Try  
> to use optim
> directly, which has quite a few methods to choose from, and one of  
> them might
> work for your problem.
>
> Dieter
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: nlme problems

Spencer Graves
          Are you familiar with Pinheiro and Bates (2000) Mixed-Effects Models
in S and S-Plus (Springer)?  I suspect that book, especially the latter
half, might contain the information you seek.

          spencer graves
p.s.  PLEASE do read the posting guide!
"www.R-project.org/posting-guide.html".  Anecdotal evidence suggests
that posts more consistent with that guide tend to receive quicker, more
useful replies.

Ken Beath wrote:

> I meant fitting not maximising, it is a nonlinear mixed effects  
> model, with both fixed and random effects. My assumption is that for  
> the function I am using the approximation approach used in nlme is  
> not quite close enough, and nothing much that I can do, except for  
> looking at starting values. I was hoping that someone would have  
> other suggestions, so I will keep attempting to understand the  
> control parameters.  I can add an extra parameter to the model and  
> obtain a worse fit.
>
> Ken
>
> Dieter Menne writes:
>
>>>I'm maximising a reasonably complex function using nlme (version
>>>3.1-65, have also tried 3.1-66) and am having trouble with fixed
>>>parameter estimates slightly away from the maximum of the log
>>>likelihood. I have profiled the log likelihood and it is a parabola
>>>but with sum dips. Interestingly changing the parameterisation moves
>>>the dips around slightly. Unfortunately the PNLS step is finding a
>>>maximum at the dips rather than the mle. I have tried using starting
>>>values for the fixed parameters without change. Any ideas ?
>>
>>Ken,
>>
>>you should not use nlme for "maximising a complex function",  
>>because it's a
>>rather specialized tool for mixed-model statistical analysis. Try  
>>to use optim
>>directly, which has quite a few methods to choose from, and one of  
>>them might
>>work for your problem.
>>
>>Dieter
>>
>
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

--
Spencer Graves, PhD
Senior Development Engineer
PDF Solutions, Inc.
333 West San Carlos Street Suite 700
San Jose, CA 95110, USA

[hidden email]
www.pdf.com <http://www.pdf.com>
Tel:  408-938-4420
Fax: 408-280-7915

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html