StandardFrequentistDiscovery.C File Reference

Detailed Description

StandardFrequentistDiscovery

This is a standard demo that can be used with any ROOT file prepared in the standard way. You specify:

• name for input ROOT file
• name of workspace inside ROOT file that holds model and data
• name of ModelConfig that specifies details for calculator tools
• name of dataset

With default parameters the macro will attempt to run the standard hist2workspace example and read the ROOT file that it produces.

 
=== Using the following for ModelConfigNull ===
Observables:             RooArgSet:: = (obs_x_channel1)
Parameters of Interest:  RooArgSet:: = (SigXsecOverSM)
Nuisance Parameters:     RooArgSet:: = (alpha_syst3,beta_syst2,gamma_stat_channel1_bin_0,gamma_stat_channel1_bin_1)
Global Observables:      RooArgSet:: = (nominalLumi,nom_alpha_syst1,nom_beta_syst2,nom_alpha_syst3,nom_gamma_stat_channel1_bin_0,nom_gamma_stat_channel1_bin_1)
PDF:                     RooProdPdf::model_channel1[ lumiConstraint * alpha_syst1Constraint * beta_syst2Constraint * alpha_syst3Constraint * gamma_stat_channel1_bin_0_constraint * gamma_stat_channel1_bin_1_constraint * channel1_model(obs_x_channel1) ] = 0.208662
Snapshot:                
  1) 0x55d0cf3e8720 RooRealVar:: SigXsecOverSM = 0 +/- 0  L(0 - 3)  "SigXsecOverSM"
 
 
=== Using the following for ModelConfig ===
Observables:             RooArgSet:: = (obs_x_channel1)
Parameters of Interest:  RooArgSet:: = (SigXsecOverSM)
Nuisance Parameters:     RooArgSet:: = (alpha_syst3,beta_syst2,gamma_stat_channel1_bin_0,gamma_stat_channel1_bin_1)
Global Observables:      RooArgSet:: = (nominalLumi,nom_alpha_syst1,nom_beta_syst2,nom_alpha_syst3,nom_gamma_stat_channel1_bin_0,nom_gamma_stat_channel1_bin_1)
PDF:                     RooProdPdf::model_channel1[ lumiConstraint * alpha_syst1Constraint * beta_syst2Constraint * alpha_syst3Constraint * gamma_stat_channel1_bin_0_constraint * gamma_stat_channel1_bin_1_constraint * channel1_model(obs_x_channel1) ] = 0.208662
Snapshot:                
  1) 0x55d0cf3e7a60 RooRealVar:: SigXsecOverSM = 1 +/- 0  L(0 - 3)  "SigXsecOverSM"
 
[#0] PROGRESS:Generation -- Test Statistic on data: 2.00306
[#1] INFO:InputArguments -- Profiling conditional MLEs for Null.
[#1] INFO:InputArguments -- Using a ToyMCSampler. Now configuring for Null.
[#0] PROGRESS:Generation -- generated toys: 500 / 1000
[#1] INFO:InputArguments -- Profiling conditional MLEs for Alt.
[#1] INFO:InputArguments -- Using a ToyMCSampler. Now configuring for Alt.
[#0] PROGRESS:Generation -- generated toys: 500 / 1000
 
Results HypoTestCalculator_result: 
 - Null p-value = 0.514 +/- 0.0158052
 - Significance = -0.0351 +/- 0.0396421 sigma
 - Number of Alt toys: 1000
 - Number of Null toys: 1000
 - Test statistic evaluated on data: 2.00306
 - CL_b: 0.514 +/- 0.0158052
 - CL_s+b: 0.746 +/- 0.0137653
 - CL_s: 1.45136 +/- 0.0520472
total CPU time: 10.33
total real time: 10.3892
(double) 0.51400000

 
#include "TFile.h"
#include "TROOT.h"
#include "TH1F.h"
#include "TF1.h"
#include "TCanvas.h"
#include "TStopwatch.h"
 
#include "RooWorkspace.h"
#include "RooAbsData.h"
#include "RooRandom.h"
#include "RooRealSumPdf.h"
#include "RooNumIntConfig.h"
 
#include "RooStats/ModelConfig.h"
#include "RooStats/ToyMCImportanceSampler.h"
#include "RooStats/HypoTestResult.h"
#include "RooStats/HypoTestPlot.h"
#include "RooStats/SamplingDistribution.h"
#include "RooStats/ProfileLikelihoodTestStat.h"
#include "RooStats/SimpleLikelihoodRatioTestStat.h"
#include "RooStats/ProfileLikelihoodCalculator.h"
#include "RooStats/LikelihoodInterval.h"
#include "RooStats/LikelihoodIntervalPlot.h"
 
#include "RooStats/FrequentistCalculator.h"
#include "TSystem.h"
 
#include <vector>
 
using namespace RooFit;
using namespace RooStats;
 
double StandardFrequentistDiscovery(const char *infile = "", const char *workspaceName = "channel1",
                                    const char *modelConfigNameSB = "ModelConfig", const char *dataName = "obsData",
                                    int toys = 1000, double poiValueForBackground = 0.0, double poiValueForSignal = 1.0)
{
 
   // The workspace contains the model for s+b. The b model is "autogenerated"
   // by copying s+b and setting the one parameter of interest to zero.
   // To keep the script simple, multiple parameters of interest or different
   // functional forms of the b model are not supported.
 
   // for now, assume there is only one parameter of interest, and these are
   // its values:
 
   // -------------------------------------------------------
   // First part is just to access a user-defined file
   // or create the standard example file if it doesn't exist
   const char *filename = "";
   if (!strcmp(infile, "")) {
      filename = "results/example_channel1_GammaExample_model.root";
      bool fileExist = !gSystem->AccessPathName(filename); // note opposite return code
      // if file does not exists generate with histfactory
      if (!fileExist) {
         // Normally this would be run on the command line
         cout << "will run standard hist2workspace example" << endl;
         gROOT->ProcessLine(".! prepareHistFactory .");
         gROOT->ProcessLine(".! hist2workspace config/example.xml");
         cout << "\n\n---------------------" << endl;
         cout << "Done creating example input" << endl;
         cout << "---------------------\n\n" << endl;
      }
 
   } else
      filename = infile;
 
   // Try to open the file
   TFile *file = TFile::Open(filename);
 
   // if input file was specified but not found, quit
   if (!file) {
      cout << "StandardRooStatsDemoMacro: Input file " << filename << " is not found" << endl;
      return -1;
   }
 
   // -------------------------------------------------------
   // Tutorial starts here
   // -------------------------------------------------------
 
   TStopwatch *mn_t = new TStopwatch;
   mn_t->Start();
 
   // get the workspace out of the file
   RooWorkspace *w = (RooWorkspace *)file->Get(workspaceName);
   if (!w) {
      cout << "workspace not found" << endl;
      return -1.0;
   }
 
   // get the modelConfig out of the file
   ModelConfig *mc = (ModelConfig *)w->obj(modelConfigNameSB);
 
   // get the data out of the file
   RooAbsData *data = w->data(dataName);
 
   // make sure ingredients are found
   if (!data || !mc) {
      w->Print();
      cout << "data or ModelConfig was not found" << endl;
      return -1.0;
   }
 
   RooRealVar *firstPOI = (RooRealVar *)mc->GetParametersOfInterest()->first();
   firstPOI->setVal(poiValueForSignal);
   mc->SetSnapshot(*mc->GetParametersOfInterest());
   // create null model
   ModelConfig *mcNull = mc->Clone("ModelConfigNull");
   firstPOI->setVal(poiValueForBackground);
   mcNull->SetSnapshot(*(RooArgSet *)mcNull->GetParametersOfInterest()->snapshot());
 
   // ----------------------------------------------------
   // Configure a ProfileLikelihoodTestStat and a SimpleLikelihoodRatioTestStat
   // to use simultaneously with ToyMCSampler
   ProfileLikelihoodTestStat *plts = new ProfileLikelihoodTestStat(*mc->GetPdf());
   plts->SetOneSidedDiscovery(true);
   plts->SetVarName("q_{0}/2");
 
   // ----------------------------------------------------
   // configure the ToyMCImportanceSampler with two test statistics
   ToyMCSampler toymcs(*plts, 50);
 
   // Since this tool needs to throw toy MC the PDF needs to be
   // extended or the tool needs to know how many entries in a dataset
   // per pseudo experiment.
   // In the 'number counting form' where the entries in the dataset
   // are counts, and not values of discriminating variables, the
   // datasets typically only have one entry and the PDF is not
   // extended.
   if (!mc->GetPdf()->canBeExtended()) {
      if (data->numEntries() == 1) {
         toymcs.SetNEventsPerToy(1);
      } else
         cout << "Not sure what to do about this model" << endl;
   }
 
   // instantiate the calculator
   FrequentistCalculator freqCalc(*data, *mc, *mcNull, &toymcs);
   freqCalc.SetToys(toys, toys); // null toys, alt toys
 
   // Run the calculator and print result
   HypoTestResult *freqCalcResult = freqCalc.GetHypoTest();
   freqCalcResult->GetNullDistribution()->SetTitle("b only");
   freqCalcResult->GetAltDistribution()->SetTitle("s+b");
   freqCalcResult->Print();
   double pvalue = freqCalcResult->NullPValue();
 
   // stop timing
   mn_t->Stop();
   cout << "total CPU time: " << mn_t->CpuTime() << endl;
   cout << "total real time: " << mn_t->RealTime() << endl;
 
   // plot
   TCanvas *c1 = new TCanvas();
   HypoTestPlot *plot = new HypoTestPlot(*freqCalcResult, 100, -0.49, 9.51);
   plot->SetLogYaxis(true);
 
   // add chi2 to plot
   int nPOI = 1;
   TF1 *f = new TF1("f", TString::Format("1*ROOT::Math::chisquared_pdf(2*x,%d,0)", nPOI), 0, 20);
   f->SetLineColor(kBlack);
   f->SetLineStyle(7);
   plot->AddTF1(f, TString::Format("#chi^{2}(2x,%d)", nPOI));
 
   plot->Draw();
   c1->SaveAs("standard_discovery_output.pdf");
 
   return pvalue;
}

Authors

Sven Kreiss, Kyle Cranmer

Definition in file StandardFrequentistDiscovery.C.