Re: multimin convergence problem

[Brian Gough <bjg at network-theory dot co dot uk>]

Roland Roberts writes:
 > Thanks for looking at this; I finally had time to go back and have a
 > second look.  I have the scale problem fixed as well as the
 > derivatives and am now getting sensible values for the covariance.  I
 > still have problems with getting NaNs during the solution but I
 > suspect this is a round-off and termination condition issue.  Or it
 > may be that near the solution, the function is not really unimodal as
 > I've managed to get several different solutions, all similar but well
 > outside one another's variance estimates.

I think this is a hard problem to minimise using only total first
derivatives.  The least squares multifit routines should be able to do
better because they will make use of the structure of the problem and
the derivatives of each component individually.

Brian