Hi Michael, Difficult to give an answer to such a general question,but maybe some interesting pointers: 1) Did you provide expressions for the derivatives of your objective function (chi2 in your case) wrt your fit parameters ? If not, it is worth trying. It will increase speed and maybe provide some more stability. 2) Are you fitting several parameters simultaneously ? If yes, try leaving one parameter free at a time. In your final step, where you have approached the minimum closer, you should leave all parameters free in order to get a reliable error estimation. Eddy > Dear rooters, > I'm using TMinuit class with some complex theoretical function > for minimization of chi2 for set of data points. > Often I get following messages: > MIGRAD FAILS TO FIND IMPROVEMENT > MIGRAD TERMINATED WITHOUT CONVERGENCE. > Changing of initial values and errors doesn't help. > What can be done to avoid this problem? > I'am interesting in parameter errors. > But errors that minuit returns in this case are invalid. > Thanks, > Michael > > Eddy A.J.M. Offermann Renaissance Technologies Corp. Route 25A, East Setauket NY 11733 e-mail: eddy@rentec.com http://www.rentec.com
This archive was generated by hypermail 2b29 : Thu Jan 01 2004 - 17:50:11 MET