[R] Problem fitting a non-linear regression model with nls

[Nathalie Yauschew-Raguenes]

Actually, the data that I used are measurements of plant growth during
an entire year.It is usual to model the growth with logistic models.
I have already tried the simple logistic model (which works). But the
problem is that with this model the inflexion point occurs half-way up
or down the logistic curve.
Thats why, despite the small amount of measurements, I wanted to try the
generalized logistic model proposed by richards.

So I will still try the nls2 package, just in case. And if it doesn't
work, I'll use "a more parsimonious model" as you two have suggested.
Thank you for your answers

-- 
Nathalie YAUSCHEW-RAGUENES
Ph.D Student
Unité de Recherches Ecologie Fonctionnelle et Physique de l'Environnement