Re: [R] bug in nls?

From: Berwin A Turlach <berwin_at_maths.uwa.edu.au>
Date: Fri, 27 Jun 2008 02:59:20 +0800

G'day Petr,

On Thu, 26 Jun 2008 13:57:39 +0200
Petr PIKAL <petr.pikal_at_precheza.cz> wrote:

> I just encountered a strange problem with nls formula. I tried to use
> nls in cycle but I was not successful. I traced the problem to some
> parse command.
>
> [...]
>
>
> I am not sure if this behaviour is a bug or feature. [...]

It is definitely a feature.

It is an error to believe that all modelling functions that use modelling formulae use the same syntax for their modelling formulae. This is, perhaps, easiest realised by observing how lm() and nls() interpret "*" and "/" in model formulae.

In nls(), "[..]" can be used to index parameters, if the parameter is allowed to change between groups in the data. This seems to be a little known feature, though there is an example that uses that feature in MASS. The contributed documentation "An Introduction to R: Software for Statistical Modelling & Computing" by Petra Kuhnert and Bill Venables, available from CRAN, also has such an example on pages 134  and 230.

The fact that nls() allows you to use "[..]" to index parameters in the model formulae seems to conflict with the way you wanted to specify the observed values in the formula. I guess Gabor's solution is a fix for your problem.

Cheers,

        Berwin


R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Thu 26 Jun 2008 - 19:36:56 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Fri 27 Jun 2008 - 10:31:25 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive