I'm having trouble fitting a histogram to Landau distribution in a limited variable range. Here's a macro, which will build a histogram, fill it and try to fit it to Landau. The fit always fails (cannot find an appropriate value for fit parameters), and I don't know what's wrong. I've tried helping the fitter by providing a reasonable starting point for the fit, but it still doesn't work. Any idea what I might be doing wrong? I'm running Root4STAR 3.02/07 Thanx, Vladimir. _______________________________________- #include <TMath.h> Double_t fitFunction(Double_t *x, Double_t *par) { Double_t xx = x[0]; return &par[0]*TMath::Landau(xx,.02,.005); } void macro() { TH1 *histo = new TH1F("histo","pPt",19,-0.002,0.19); histo->SetEntries(174); histo->SetDirectory(0); histo->SetBinContent(1,12); histo->SetBinContent(2,22); histo->SetBinContent(3,18); histo->SetBinContent(4,10); histo->SetBinContent(5,8); histo->SetBinContent(6,8); histo->SetBinContent(7,3); histo->SetBinContent(8,3); histo->SetBinContent(9,2); histo->SetBinContent(10,3); histo->SetBinContent(11,1); histo->SetBinContent(12,1); histo->SetBinContent(13,1); histo->SetBinContent(14,1); histo->SetBinContent(15,7); histo->SetBinContent(16,3); histo->SetBinContent(17,8); histo->SetBinContent(19,4); histo->SetMarkerStyle(20); histo->Draw(""); TF1 *fun = new TF1("fun",fitFunction,0.03,.12,1); fun->SetParameter(0,140.0); histo->Fit("fun","R"); }
This archive was generated by hypermail 2b29 : Sat Jan 04 2003 - 23:50:46 MET