JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio Class Reference

Implementation of the Poisson log-likelihood ratio test. More...

#include <JTestPoissonLogLikelihoodRatio.hh>

Inheritance diagram for JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio:

Public Member Functions
	JTestPoissonLogLikelihoodRatio ()
	Default constructor. More...
void	test (const TObject *o1, const TObject *o2) override
	Applies a Poissonian log-likelihood ratio test to the two given histograms. More...
std::istream &	read (std::istream &in) override
	Read test parameters from input. More...
virtual std::ostream &	write (std::ostream &out, const char delimiter= ' ', const bool onlyFailures=false) const
	Write test result to output. More...
virtual void	save (TFile *f, const std::string &path, const bool onlyFailures=false) const
	Writes the test result to root file. More...
const std::string &	getTestName () const
	Get test name. More...
const std::string &	getResultType () const
	Get result type. More...

Protected Attributes
const std::string	testName
	test name More...
const std::string	resultType
	test result type More...

Private Attributes
double	threshold
	threshold chi-square to decide if test is passed. More...

Detailed Description

Implementation of the Poisson log-likelihood ratio test.

The first histogram is treated as an Asimov dataset corresponding to a given null hypothesis,
which is compared to an alternative hypothesis given by the second histogram.

This class is derived from the abstract class JTest_t(). For a general description of the implementation of this and other tests derived from JTest_t(), see its documentation.

Definition at line 27 of file JTestPoissonLogLikelihoodRatio.hh.

Constructor & Destructor Documentation

JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio::JTestPoissonLogLikelihoodRatio ( )

inline

Default constructor.

Definition at line 35 of file JTestPoissonLogLikelihoodRatio.hh.

                                     :
      JTest_t("Poissonian Log-Likelihood Ratio", "NLLR")
    {}

Member Function Documentation

void JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio::test ( const TObject *  o1, const TObject *  o2  )

inlineoverridevirtual

Applies a Poissonian log-likelihood ratio test to the two given histograms.

The first histogram is treated as an Asimov dataset corresponding to a given null hypothesis.
The second histogram is treated as the expectation for the alternative hypothesis, to which the null hypothesis is compared.

Parameters

o1	First histogram
o2	Second histogram

< Penalty factor

Implements JCOMPAREHISTOGRAMS::JTest_t.

Definition at line 48 of file JTestPoissonLogLikelihoodRatio.hh.

    {
      using namespace std;
      using namespace JPP;
      
      static const double penalty = -1e9; //!< Penalty factor

      const TH1* h1 =  dynamic_cast<const TH1*>(o1);
      const TH1* h2 =  dynamic_cast<const TH1*>(o2);

      if (h1 == NULL || h2 == NULL) {
        THROW(JValueOutOfRange, "JTestPoissonLogLikelihood::test(): Could not cast given TObjects to TH1.");
      }

      if(h1->GetNbinsX() != h2->GetNbinsX() ||
         h1->GetNbinsY() != h2->GetNbinsY() ||
         h1->GetNbinsZ() != h2->GetNbinsZ()) {
        THROW(JValueOutOfRange, "JTestPoissonLogLikelihood::test(): Histograms with different binning. The objects: " <<
              h1->GetName() << " and " << h2->GetName() << " can not be compared." << endl);
      }

      TH1* h3 = (TH1*) h1->Clone(h1->GetName() == h2->GetName() ?
                                 MAKE_CSTRING(h1->GetName()                            << "_" << testName) :
                                 MAKE_CSTRING(h1->GetName() << "_VS_" << h2->GetName() << "_" << testName));

      h3->Reset();

      double LnLratio = 0.0;

      for (int i=1 ; i <= h1->GetNbinsX() ; ++i){
        for (int j=1 ; j <= h1->GetNbinsY() ; ++j){
          for (int k=1 ; k <= h1->GetNbinsZ() ; ++k){

            double contribution;

            const double n0 = h1->GetBinContent(i,j,k);
            const double n1 = h2->GetBinContent(i,j,k);

            if        (n0 > 0.0 && n1 > 0.0) {
              contribution = 2 * (n0 - n1 - n0 * log(n0/n1));
            } else if (n0 > 0.0 || n1 > 0.0) {
              contribution = penalty;
            } else {
              contribution = 0.0;
            }

            h3->SetBinContent(i,j,k, contribution);

            LnLratio -= contribution;
          }
        }
      }

      const bool passed = (LnLratio < threshold);

      const JResultTitle title(testName, resultType, passed, LnLratio);

      h3->SetTitle(title.getTitle().c_str());
      h3->GetYaxis()->SetTitle(resultType.c_str());

      const JTestResult r (testName,
                           JRootObjectID(MAKE_STRING(h1->GetDirectory()->GetPath() << h1->GetName())),
                           JRootObjectID(MAKE_STRING(h2->GetDirectory()->GetPath() << h1->GetName())),
                           resultType, LnLratio, threshold, h3, passed);
      
      this->push_back(r);
    }

std::istream& JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio::read ( std::istream &  in )

inlineoverridevirtual

Read test parameters from input.

Parameters

in	input stream

Returns

input stream

Implements JCOMPAREHISTOGRAMS::JTest_t.

Definition at line 123 of file JTestPoissonLogLikelihoodRatio.hh.

    {
      using namespace JPP;
      
      in >> threshold;

      if (!(threshold > 0.0)) {
        THROW(JValueOutOfRange, "JTestPoissonLogLikelihoodRatio::read(): Given chi-square threshold " << threshold << " is invalid");
      }
       
      return in;
    }

virtual std::ostream& JCOMPAREHISTOGRAMS::JTest_t::write ( std::ostream &  out, const char  delimiter = ' ', const bool  onlyFailures = false  ) const

inlinevirtualinherited

Write test result to output.

Parameters

out	output stream
delimiter	field delimiter
onlyFailures	if true, write only failures.

Returns

output stream

Definition at line 84 of file JTest_t.hh.

    {
      using namespace std;
      using namespace JPP;

      for (vector<JTestResult>::const_iterator r = this->begin() ; r != this->end() ; ++r) {

        if (onlyFailures && r->passed) { continue; }
        
        print(out, *r, delimiter, true);
      }
      
      return out;
    }

virtual void JCOMPAREHISTOGRAMS::JTest_t::save ( TFile *  f, const std::string &  path, const bool  onlyFailures = false  ) const

inlinevirtualinherited

Writes the test result to root file.

Parameters

f	A ROOT file
path	Path in root file.
onlyFailures	If true, write only failures.

Definition at line 108 of file JTest_t.hh.

    {
      using namespace std;
      using namespace JPP;

      if (f->GetDirectory(path.c_str())==0) {
        f->mkdir(path.c_str());
      }
      
      f->cd(path.c_str());

      for (vector<JTestResult>::const_iterator r = this->begin() ; r != this->end() ; ++r) {

        if (onlyFailures && r->passed) { continue; }
        
        r->obj->Write();
      }
    }

const std::string& JCOMPAREHISTOGRAMS::JTest_t::getTestName ( ) const

inlineinherited

Get test name.

Returns

test name

Definition at line 135 of file JTest_t.hh.

    {
      return testName;
    }

const std::string& JCOMPAREHISTOGRAMS::JTest_t::getResultType ( ) const

inlineinherited

Get result type.

Returns

result type

Definition at line 146 of file JTest_t.hh.

    {
      return resultType;
    }

Member Data Documentation

double JCOMPAREHISTOGRAMS::JTestPoissonLogLikelihoodRatio::threshold

private

threshold chi-square to decide if test is passed.

Definition at line 138 of file JTestPoissonLogLikelihoodRatio.hh.

const std::string JCOMPAREHISTOGRAMS::JTest_t::testName

protectedinherited

test name

Definition at line 180 of file JTest_t.hh.

const std::string JCOMPAREHISTOGRAMS::JTest_t::resultType

protectedinherited

test result type

Definition at line 181 of file JTest_t.hh.

---

The documentation for this class was generated from the following file:

• JTestPoissonLogLikelihoodRatio.hh