Dear R Gang,
I'm interested in using R and the nls package for fitting kinetic
models. I'm having some difficulty getting a model specified for
nls though. The math for the model that I want to fit is
dg(t)/dt = K1 f(t) - k2 g(t)
where g(t) and f(t) are measured data at a sequence of times
[EMAIL PROTECTED] (Michael A. Miller) writes:
> Dear R Gang,
>
> I'm interested in using R and the nls package for fitting kinetic
> models. I'm having some difficulty getting a model specified for
> nls though. The math for the model that I want to fit is
>
>dg(t)/dt = K1 f(t) - k2 g(t)
>
I did not know about stepsize being an issue. I had thought that
problems with convergence in this case were due to bad approximations of
the finite difference gradient. I guessed that around the optimum,
numerical errors would come to dominate the gradient calculations,
causing convergence to f
[EMAIL PROTECTED] writes:
> I did not know about stepsize being an issue. I had thought that
> problems with convergence in this case were due to bad approximations of
> the finite difference gradient. I guessed that around the optimum,
> numerical errors would come to dominate the gradient calc