Dear all, I am currently experimenting gnumeric's solver. It is a very useful tool, congratulations!
One feature that I miss, though, is the following. Often in data inversion problems, one try to minimize a cost function which is (in the gaussian case) a sum of squared residuals divided by squared confidence interval. When reaching the minimum of the cost function, one evaluates the confidence intervals of the tuning parameters by using the confidence intervals of the data and by approximating the model by its tangent. Could this feature be implemented in gnumeric? It would make the solver a lot more useful. Thanks and best regards, Frédéric Parenin -- http://parrenin.frederic.free.fr/ _______________________________________________ gnumeric-list mailing list [email protected] https://mail.gnome.org/mailman/listinfo/gnumeric-list
