Re: Re: StartingParameters
- To: mathgroup at smc.vnet.net
- Subject: [mg16605] Re: [mg16503] Re: [mg16447] StartingParameters
- From: "Rajdeep S. Kalgutkar" <rajdeep at chem.nwu.edu>
- Date: Wed, 17 Mar 1999 23:55:09 -0500
- Sender: owner-wri-mathgroup at wolfram.com
Oops,
I messed up my previous reply... The syntax for NonlinearRegress is as
follows (as others have already pointed out correctly):
NonlinearRegress[datatable, p[t], t, {{kon,0.2},{koff,10^8}}]
You can also specify your parameters as follows:
{{kon,min,max},{koff,min,max}}
OR
{{kon,0.2,min,max},{koff,10^8,min,max}}
However you cannot use constraints (min and max) for one parameter, say
kon and not for the other (koff). Use the ShowProgress->True option to see
how your regression is proceeding. This feature is useful for many
parameter models where you want to know the points through which the
Levenberg-Marquardt algorithm proceeded.
Sorry about the mess up...
rajdeep
>
> Katarina,
>
> Take the starting parameters statement out.
> e.g. NonlinearRegress[datatable, p[t], t, {kon, koff}, {{kon,
> 0.2},{koff,10^8}}]
> NonlinearFit has the same syntax.
>
> Hope this helps...
> rajdeep
>
> At 02:21 AM 3/13/99 -0500, you wrote:
> >Hello,
> > I am trying to use the option of giving starting parameters for a
> >NonlinearRegress command. I can't figure out the correct syntax for
> >this. Can anyone let me know the correct way to list the starting values
> >for two parameters in NonlinearRegress (or I think it should be the same
> >as NonlinearFit also)
> >
> >Here is what I am trying:
> >NonlinearRegress[datatable, p[t], t ,{kon, koff}, StartingParameters ->
> >{{kon, 0.2},{koff,10^8}}]
> >
> >I would like to have the data in the table (datatable) fit to the model
> >( p[t]) with the variables ( t) and the parameters ( kon and koff)
> >staring at 0.2 for kon and 10^8 for koff. It doesn't fit when I try
> >without giving the starting parameters. What is the correct way to put
> >the starting parameters in the above statement?
> >
> >I hope this question makes sense. Any help is greatfully appreciated.
> >
> >Thank you,
> > Katarina
> >
> >Katarina Midelfort
> >Center for Biophysics and Computational Biology
> >University of Illinois
> >midelfor at uiuc.edu
> >
> >
>
>
>