Hi all, when I fit the histogram, it happens sometimes that the fit procedure never ends. The only way to end the program is to interrupt it and of course all the results are lost. This is very troublesome. Is there anything I can do about it? Is it possible to handle this by some exception? Thanks for advice. I use root 3.02/02 on SuSE Linux 6.3 (i386) - Kernel 2.2.16 (pts/7). Miro Helbich root [7] fMassSpectrum->Fit(func->GetName(),"RIV","E"); ********** ** 129 **SET ERR 1 ********** PARAMETER DEFINITIONS: NO. NAME VALUE STEP SIZE LIMITS 1 p0 2.00000e+01 6.00000e+00 no limits 2 p1 1.02000e+00 3.06000e-01 no limits 3 p2 9.99999e-03 3.00000e-03 no limits 4 p3 5.00000e+00 1.50000e+00 no limits 5 p4 5.00000e-01 1.50000e-01 no limits 6 p5 9.86000e-01 2.95800e-01 no limits ********** ** 130 **FIX 6 ********** ********** ** 131 **SET PRINT 0 ********** ********** ** 132 **MIGRAD 5000 0.00026 ********** MINUIT WARNING IN MIGRAD ============== Negative diagonal element 1 in Error Matrix MINUIT WARNING IN MIGRAD ============== Negative diagonal element 2 in Error Matrix MINUIT WARNING IN MIGRAD ============== Negative diagonal element 3 in Error Matrix MINUIT WARNING IN MIGRAD ============== Negative diagonal element 4 in Error Matrix MINUIT WARNING IN MIGRAD ============== Negative diagonal element 5 in Error Matrix MINUIT WARNING IN MIGRAD ============== 1469.61 added to diagonal of error matrix EIGENVALUES OF SECOND-DERIVATIVE MATRIX: -2.0594e+01 1.0000e+00 1.0001e+00 1.0048e+00 2.2589e+01 MINUIT WARNING IN MIGRAD ============== MATRIX FORCED POS-DEF BY ADDING 20.616870 TO DIAGONAL.
This archive was generated by hypermail 2b29 : Tue Jan 01 2002 - 17:51:09 MET