R help - Nov 2009 - Testing treatment effects on exponential decay models

Hello all:

I would like to test whether there are treatment effects on decomposition
rate, and I would like to inquire about the best, most appropriate means
using R.

I have plant decomposition data that is generally considered to follow an
exponential decay model as follows:

Wt = Wi * exp(-k * t)

Where Wt and Wi are the weights of the plant material at time t and 0,
respectively. k is a constant describing decomposition rate and is usually
reported in the literature.

Is it possible to fit a non-linear model as above and test for effects of
two, independent, treatment factors + the interaction?  I have used nls() to
fit the above model for each treatment and approximate k, but I would like
to examine treatment effects on these fits as I might using glm().  If I can
get passed this hurdle, I may also inquire about adding a random effect as
well.

If it helps, I can post a subset of data.  Thanks for any help.

-
Justin Montemarano
Graduate Student
Kent State University - Biological Sciences

http://www.montegraphia.com

	[[alternative HTML version deleted]]