[R] NLS "Singular Gradient" Error

[Ben Bolker]

Ben Bolker <bolker <at> ufl.edu> writes:

>   You should really try the methods I suggested ... you can get
> a closed-form expression for the number eaten as a function of the
> other parameters using the Lambert W function.  I don't think what
> you're doing (with Ne on both sides of the equation) is ever going to
> work ...
> 
>   Ben Bolker

  PS see p. 355 in http://people.biology.ufl.edu/bolker/emdbook/book.pdf ,
or p. 269 in the published version ... The example there assumes binomial
error, and does maximum likelihood fits, but you could adapt those examples
to least-squares as well.