Tried to scale the Covariance matrix, as explained here: http://www.orbitals.com/self/least/least.htm.
This does not work better.
Also replaced "errors" to "weights" to the multifit_covar(), to better determine control calculations.
task #7822(https://gna.org/task/index.php?7822): Implement user function to estimate R2eff and associated errors for exponential curve fitting.
Authored by: tlinnet 2014-08-28
Parent: [r25390]
Child: [r25392]
