[R-sig-eco] help radfit()

[Jari Oksanen]

Negative values of what? If it is AIC, it is not a problem. With AIC, only differences are meaningful. The observed values can be negative.

Cheers, Jari Oksanen

Sent from my iPad

> On 29.11.2014, at 19.56, Manoeli Lupatini <mlupatini at gmail.com> wrote:
> 
> Dear all,
> 
> I am working with radfit() function in vegan with a df which contains a big
> amount of zeros. When is not zero, I have numbers with comma, which
> represent proportions. I am using the family Gamma. I got negative values
> for some models. Below an example of the output:
> 
>      Null  Preemption   Lognormal        Zipf  Mandelbrot
> 37  694.8004  -413.17581  -565.23622  492.945299  -482.93299
> 38  415.2763  -340.93024  -363.86510  469.338760  -379.28155
> 39 1221.0254  -310.94620 -1490.60959 1131.261212  -342.56346
> 40 1448.9174  -328.61790  -794.12383  761.840479  -439.40301
> 41 1007.8350  -376.34689  -493.21855  455.072273  -486.60574
> 
> Someone can explain if is a problema to get this negative values?
> 
> Thanks for your help,
> 
> Manoeli
> 
> 
> -- 
> 
> Manoeli Lupatini
> 
> Eng. Agrônoma
> Ms. em Ciência do Solo,
> Doutoranda em Ciência do Solo
> Programa de Pós-graduação em Ciência do Solo
> Departamento de Solos, UFSM, Santa Maria
> (55)81262295
> 
>    [[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology