ROOT logo
ROOT » ROOFIT » ROOSTATS » RooStats::FeldmanCousins

class RooStats::FeldmanCousins: public RooStats::IntervalCalculator


The FeldmanCousins class (like the Feldman-Cousins technique) is essentially a specific configuration of the more general NeymanConstruction. It is a concrete implementation of the IntervalCalculator interface that, which uses the NeymanConstruction in a particular way. As the name suggests, it returns a ConfidenceInterval. In particular, it produces a RooStats::PointSetInterval, which is a concrete implementation of the ConfInterval interface.

The Neyman Construction is not a uniquely defined statistical technique, it requires that one specify an ordering rule or ordering principle, which is usually incoded by choosing a specific test statistic and limits of integration (corresponding to upper/lower/central limits). As a result, this class must be configured with the corresponding information before it can produce an interval.

In the case of the Feldman-Cousins approach, the ordering principle is the likelihood ratio -- motivated by the Neyman-Pearson lemma. When nuisance parameters are involved, the profile likelihood ratio is the natural generalization. One may either choose to perform the construction over the full space of the nuisance parameters, or restrict the nusiance parameters to their conditional MLE (eg. profiled values).



Function Members (Methods)

public:
virtual~FeldmanCousins()
voidAdditionalNToysFactor(double fact)
static TClass*Class()
virtual Double_tConfidenceLevel() const
voidCreateConfBelt(bool flag = true)
RooStats::FeldmanCousinsFeldmanCousins(const RooStats::FeldmanCousins&)
RooStats::FeldmanCousinsFeldmanCousins(RooAbsData& data, RooStats::ModelConfig& model)
voidFluctuateNumDataEntries(bool flag = true)
RooStats::ConfidenceBelt*GetConfidenceBelt()
virtual RooStats::PointSetInterval*GetInterval() const
RooAbsData*GetPointsToScan()
RooStats::TestStatSampler*GetTestStatSampler() const
virtual TClass*IsA() const
RooStats::IntervalCalculator&RooStats::IntervalCalculator::operator=(const RooStats::IntervalCalculator&)
voidSaveBeltToFile(bool flag = true)
virtual voidSetConfidenceLevel(Double_t cl)
virtual voidSetData(RooAbsData&)
virtual voidSetModel(const RooStats::ModelConfig&)
voidSetNBins(Int_t bins)
virtual voidSetNuisanceParameters(const RooArgSet&)
voidSetParameterPointsToTest(RooAbsData& pointsToTest)
virtual voidSetParameters(const RooArgSet&)
virtual voidSetPdf(RooAbsPdf&)
voidSetPOIPointsToTest(RooAbsData& poiToTest)
virtual voidSetTestSize(Double_t size)
virtual voidShowMembers(TMemberInspector&)
virtual Double_tSize() const
virtual voidStreamer(TBuffer&)
voidStreamerNVirtual(TBuffer& ClassDef_StreamerNVirtual_b)
voidUseAdaptiveSampling(bool flag = true)
private:
voidCreateParameterPoints() const
voidCreateTestStatSampler() const

Data Members

private:
Bool_tfAdaptiveSamplingcontrols use of adaptive sampling algorithm
Double_tfAdditionalNToysFactorgive user ability to ask for more toys
RooStats::ConfidenceBelt*fConfBelt
Bool_tfCreateBeltcontrols use if ConfidenceBelt should be saved to a TFile
RooAbsData&fDatadata set
Bool_tfDoProfileConstructioninstead of full construction over nuisance parametrs, do profile
Bool_tfFluctuateDatatell ToyMCSampler to fluctuate number of entries in dataset
RooStats::ModelConfig&fModel
Int_tfNbinsnumber of samples per variable
RooAbsData*fPOIToTestvalue of POI points to perform the construction
RooAbsData*fPointsToTestpoints to perform the construction
Bool_tfSaveBeltToFilecontrols use if ConfidenceBelt should be saved to a TFile
Double_tfSizesize of the test (eg. specified rate of Type I error)
RooStats::ToyMCSampler*fTestStatSamplerthe test statistic sampler

Class Charts

Inheritance Inherited Members Includes Libraries
Class Charts

Function documentation

FeldmanCousins(RooAbsData& data, RooStats::ModelConfig& model)
 standard constructor
~FeldmanCousins()
 destructor
if(fOwnsWorkspace && fWS) delete fWS;
void SetModel(const RooStats::ModelConfig& )
 set the model
TestStatSampler* GetTestStatSampler() const
void CreateTestStatSampler() const
 specify the Test Statistic and create a ToyMC test statistic sampler
void CreateParameterPoints() const
 specify the parameter points to perform the construction.
 allow ability to profile on some nuisance paramters
PointSetInterval* GetInterval() const
 Main interface to get a RooStats::ConfInterval.
 It constructs a RooStats::PointSetInterval.
FeldmanCousins(RooAbsData& data, RooStats::ModelConfig& model)
     FeldmanCousins();
 Common constructor
Double_t Size() const
 Get the size of the test (eg. rate of Type I error)
{return fSize;}
Double_t ConfidenceLevel() const
 Get the Confidence level for the test
{return 1.-fSize;}
void SetData(RooAbsData& )
 Set the DataSet
void SetPdf(RooAbsPdf& )
 Set the Pdf
void SetParameters(const RooArgSet& )
 specify the parameters of interest in the interval
void SetNuisanceParameters(const RooArgSet& )
 specify the nuisance parameters (eg. the rest of the parameters)
void SetParameterPointsToTest(RooAbsData& pointsToTest)
 User-defined set of points to test
void SetPOIPointsToTest(RooAbsData& poiToTest)
 User-defined set of points to test
void SetTestSize(Double_t size)
 set the size of the test (rate of Type I error) ( Eg. 0.05 for a 95% Confidence Interval)
{fSize = size;}
void SetConfidenceLevel(Double_t cl)
 set the confidence level for the interval (eg. 0.95 for a 95% Confidence Interval)
{fSize = 1.-cl;}
RooAbsData* GetPointsToScan()
ConfidenceBelt* GetConfidenceBelt()
{return fConfBelt;}
void UseAdaptiveSampling(bool flag = true)
void AdditionalNToysFactor(double fact)
void SetNBins(Int_t bins)
{fNbins = bins;}
void FluctuateNumDataEntries(bool flag = true)
{fFluctuateData = flag;}
void SaveBeltToFile(bool flag = true)
void CreateConfBelt(bool flag = true)
{fCreateBelt = flag;}