Hi Rooters, I have a question regarding TMinuit. I have two Monte Carlo histograms (signal and background), and I am generating a fake data histogram by drawing N1 'events' out of the signal histogram, and N2 from the background histogram. I use then TMinuit to fit the fake data as the sum of the two MC histos - to see if I get numbers close to N1 and N2. I do this many times; the fit always returns about the right value for N1 and N2. However, the error returned by the fit appears to be the same every time (it slightly varies within a very small range). Has anybody seen this (or something similar) before? Is there a bug in the way the errors on the parameters are computed? I am using ROOT Version 2.22/06. Thanks for the help, Catalin Ciobanu, CDF e-mail: catutza@mps.ohio-state.edu
This archive was generated by hypermail 2b29 : Tue Jan 02 2001 - 11:50:29 MET