Problem using simpdf in subranges in different observables

Roofit and RooStats
1

Dear experts,

I am trying to do a simultaneous fit in two observables in different ranges. The range is defined with a blinding region for one variable while it is full for the other. The problem is similar if not the same as in the question: quesiton. Unfortunetely the solution that is shown is not working for me. I created this dummy code to reproduce the problem. Any help?

Bests,
Elia
reproduceProb.C (2.7 KB)

2

Hi @Elia_Giulio_Grandoni,

thank you for the question. Let me ping @jonas here.

Cheers,
Marta

3

Thanks @mczurylo,

any follow up? @jonas

Cheers,
Elia

Processing reproduceProb.C...
[#1] INFO:Eval -- RooRealVar::setRange(x) new range named 'left' created with bounds [100,150]
[#1] INFO:Eval -- RooRealVar::setRange(x) new range named 'right' created with bounds [100,100]
[#1] INFO:Eval -- RooRealVar::setRange(y) new range named 'left' created with bounds [100,120]
[#1] INFO:Eval -- RooRealVar::setRange(y) new range named 'right' created with bounds [130,150]
[#0] WARNING:InputArguments -- The parameter 'sigmaA' with range [-inf, inf] of the RooGaussian 'gaussA' exceeds the safe range of (0, inf). Advise to limit its range.
[#0] WARNING:InputArguments -- The parameter 'sigmaB' with range [-inf, inf] of the RooGaussian 'gaussB' exceeds the safe range of (0, inf). Advise to limit its range.
[#1] INFO:Minimization -- p.d.f. provides expected number of events, including extended term in likelihood.
[#1] INFO:Eval -- RooRealVar::setRange(x) new range named 'fit_nll_simPdf_combData_left' created with bounds [100,150]
[#1] INFO:Eval -- RooRealVar::setRange(y) new range named 'fit_nll_simPdf_combData_left' created with bounds [100,120]
[#1] INFO:Eval -- RooRealVar::setRange(x) new range named 'fit_nll_simPdf_combData_right' created with bounds [100,100]
[#1] INFO:Eval -- RooRealVar::setRange(y) new range named 'fit_nll_simPdf_combData_right' created with bounds [130,150]
[#1] INFO:Fitting -- RooAbsPdf::fitTo(simPdf) fixing normalization set for coefficient determination to observables in data
[#1] INFO:Fitting -- using CPU computation library compiled with -mavx512
[#1] INFO:Fitting -- RooAddition::defaultErrorLevel(nll_simPdf_combData) Summation contains a RooNLLVar, using its error level
[#1] INFO:Minimization -- RooAbsMinimizerFcn::setOptimizeConst: activating const optimization
Minuit2Minimizer: Minimize with max-calls 1000 convergence for edm < 1 strategy 1
Info in <Minuit2>: MnSeedGenerator Computing seed using NumericalGradient calculator
[#0] ERROR:Integration -- _y_sample_gaussB_over_gaussB_Int[y] : integrating with respect to the variables () on the ranges  "left,right" is not possible because the ranges are overlapping
terminate called after throwing an instance of 'std::invalid_argument'
  what():  _y_sample_gaussB_over_gaussB_Int[y] : integrating with respect to the variables () on the ranges  "left,right" is not possible because the ranges are overlapping

reproduceProb.C (3.5 KB)