[R] nls: singular convergeance

[Rolf Turner]

On 13/10/11 21:26, Redding, Matthew wrote:
> Hi Rolf and others
>
> Will this make any difference to the convergence?
     I have no idea, really.  I don't know if convergence issues even
     arise in the context of the "segmented" package.  I have never
     encountered any.

     Try it and see.  Shouldn't take more than about 10 minutes, all up.

         cheers,

             Rolf
> ----- Original Message -----
> From: Rolf Turner<rolf.turner at xtra.co.nz>
> To: Redding, Matthew
> Cc: r-help at r-project.org<r-help at r-project.org>
> Sent: Thu Oct 13 18:04:53 2011
> Subject: Re: [R] nls: singular convergeance
>
> On 13/10/11 18:02, Redding, Matthew wrote:
>> Dear R-experts,
>>
>> I have 28 data points that I would like to fit with a non linear
>> broken-stick -- with three fitted parameters.
>> When I view trace -- and use the final values as lines on the graph of
>> data -- it looks pretty good.
>>
>> Q1. Why am I getting singular convergeance?
>> Q2. Can you suggest another approach that may prove more satisfying?
> <SNIP>
>
> Have you thought of using the "segmented" package instead
> of rolling your own with nls?
>
>       cheers,
>
>           Rolf Turner