R help - Jun 2003 - Help - Curvature measures of nonlinearity

Dear colleagues,

Von Bertalanffy model is commonly adjust to data on fish length (TL) and age
(AGE)
TL= Linf*(1-exp(-K*(AGE-t0)). Linf, K and t0 are parameters of the model.
One main goal of the growth study is the comparison of growth parameter
estimates between sexes of the same species, or estimates from different
populations.
The realibility statistical tests normally applied are highly dependent on the
nonlinearity of the model used.

Are there any developed routines in R ? to:
1) calculate the maximum intrinsic curvature
2) maximum parameter affecting curvature 
3) plot the two dimensional cross sections of confidence regions (for different
alpha values) of the model parameters

Regards,
Ivone Figueiredo 
	[[alternate HTML version deleted]]

How about "rms.curv" function in the MASS library?

Ravi.

----- Original Message -----
From: Ivone Figueiredo <ivonefig at ipimar.pt>
Date: Monday, June 2, 2003 4:40 am
Subject: [R] Help - Curvature measures of nonlinearity
> Dear colleagues,
> 
> Von Bertalanffy model is commonly adjust to data on fish length 
> (TL) and age (AGE) 
> TL= Linf*(1-exp(-K*(AGE-t0)). Linf, K and t0 are parameters of the 
> model.One main goal of the growth study is the comparison of 
> growth parameter estimates between sexes of the same species, or 
> estimates from different populations. 
> The realibility statistical tests normally applied are highly 
> dependent on the nonlinearity of the model used.
> 
> Are there any developed routines in R ? to:
> 1) calculate the maximum intrinsic curvature
> 2) maximum parameter affecting curvature 
> 3) plot the two dimensional cross sections of confidence regions 
> (for different alpha values) of the model parameters
> 
> Regards,
> Ivone Figueiredo 
> 	[[alternate HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
>