The aim is fitting the following equation by optimizing the K's parameters and knowing L:
Y_fit = (Ka*Kb**L2) / (1 + K11*L + Ka*Kb*L**2)
and Y = experimental points that one want to be fitted using the customized formula above with the optimized K0 parameters.
where
K0 = array([Ka, Kb])
parameters_opt = op.minimize(np.square(Y_exp - Y_fit).sum(), K0, args=args, bounds=bounds, method="L-BFGS-B", tol=1e-6)
where args = Extra arguments passed to the objective function and its derivatives
In all previous Q&A there is discussed the tolerance parameter (tol) and so on, but I could not find any final answer how to determine the uncertainty of those parameters for the fitting in order to give a final result of the K0 parameters such as:
Ka = x1 ± ∆x1
Kb = x2 ± ∆x2
(To complement the \Chi^2 of the fitting to evaluate the Goodness of my fitting).