Hi,Rene, You know ,I fill the histogram from the root file which does not store error infomation. kskp->Draw("Mass>>etac","Ccen<0.6&&Pt<0.6&&abs(Ksmass-0.497672)<0.010"); If this means i should check the error of the histogram bins (I suppose it should be caculated automatically) when i fill a histogram from root(ntuple) file? It confused me. I also noticed if i more tighter cut, the fit quality worse. You know different cut means got differnet histogram. But if i loose cut and no no empty bins inhistogram,root got same result with mn_fit. A senior professor said that mn_fit had same problem before. Gong Datao On Wed, 26 Feb 2003, Rene Brun wrote: > Hi Gong, > > I looked at your histogram. You have a few points for which the errors > do not seem correct. I do not know how you filled your histogram. > If you add the 3 following lines > etac->SetBinError(18,20); > etac->SetBinError(23,20); > etac->SetBinError(43,20); > > to set bigger error bars for these 3 bins and fit with the simple > loglikelihood method > his->Fit(FunName,"L0"); > > then you will get a chi2/ndf = 190/189 > > Rene Brun > > On > Wed, 26 Feb 2003, Datao Gong wrote: > > > Hi,Rooters, > > I fit my ntuple with likelihood method. I found if i tightly cut, > > the fit result is much different and fit quality worse (ch2/ndf far > > away from 1). Compare to min_fit, i found it is from the empty bins > > in histogram. Likelihood method seems do not take into account > > empty bin default. (I read Burn's email in roottalk02). In my case, > > I fit my histogram with option "EMVL0", the ch2/ndf is 237/189, meanwhile, > > mn_fit give me 190/191. I know there are two empty bins in my histogram. > > If i set "W" option, the chi2/ndf is up to 3067/191. Is there something > > wrong? > > > > Gong Datao > > > > >
This archive was generated by hypermail 2b29 : Thu Jan 01 2004 - 17:50:09 MET