Jay,

I recently had a project in which I needed to test for equivalence 
between three non-linear curves . Fortunately I found a nice 
randomization test for this in the stats program that I was using 
(NCSS,  about $35 if you're a student), which I also used to do the 
initial curve-fits. It also does an F-test for curve equivalence, but 
the author maintains that this is a poor test for non-linear models. The 
randomization test allows you to choose the depth of the comparison, up 
to 100,000 Monte Carlo samples at 1000 points, overkill but interesting 
if you want to see how long it takes (several minutes).

Good luck,

Bill Porter

> I have similar problems in comparing non-linear regression lines. Here, =
> it goes what I want to compare. I have shrub biomass and pine seedling =
> density data collected in 160 50-m2 plots. I used non-linear regression =
> (y =3D b0*(1-exp(-b1^x)) to model the cumulative seedling density =
> against shrub biomass. I am interested to test if this regression curve =
> (observed pattern) differs from another similar curve (a reference =
> model), generated by using Poisson cumulative distribution function. My =
> questions are: how to compare these two non-linear regression lines or =
> the coefficients there in? Are the methods described in Zar's book and =
> elsewhere, more commonly used for comparing slopes in linear regression, =
> also applicable for non-linear regression lines? =20

Reply via email to