Factory classes to create RooFit workspaces from histograms.

This is a package that creates a RooFit probability density function from ROOT histograms of expected distributions and histograms that represent the +/- 1 sigma variations from systematic effects. The resulting probability density function can then be used with any of the statistical tools provided within RooStats, such as the profile likelihood ratio, Feldman-Cousins, etc. In this version, the model is directly fed to a likelihood ratio test, but it needs to be further factorized.

The user needs to provide histograms (in picobarns per bin) and configure the job with XML. The configuration XML is defined in the file $ROOTSYS/config/HistFactorySchema.dtd, but essentially it is organized as follows (see the examples in ${ROOTSYS}/tutorials/histfactory/)

a top level 'Combination' that is composed of:
- several 'Channels' (eg. ee, emu, mumu), which are composed of:
  - several 'Samples' (eg. signal, bkg1, bkg2, ...), each of which has:
    - a name
    - if the sample is normalized by theory (eg N = L*sigma) or not (eg. data driven)
    - a nominal expectation histogram
    - a named 'Normalization Factor' (which can be fixed or allowed to float in a fit)
    - several 'Overall Systematics' in normalization with:
      - a name
      - +/- 1 sigma variations (eg. 1.05 and 0.95 for a 5% uncertainty)
    - several 'Histogram Systematics' in shape with:
      - a name (which can be shared with the OverallSyst if correlated)
      - +/- 1 sigma variational histograms
- several 'Measurements' (corresponding to a full fit of the model) each of which specifies
  - a name for this fit to be used in tables and files
  - what is the luminosity associated to the measurement in picobarns
  - which bins of the histogram should be used
  - what is the relative uncertainty on the luminosity
  - what is (are) the parameter(s) of interest that will be measured
  - which parameters should be fixed/floating (eg. nuisance parameters)

For more documentation see CERN-OPEN-2012-016.

For tutorials see HistFactory Tutorials.

Namespaces
namespace	RooStats
	Namespace for the RooStats classes.

Classes
class	RooStats::HistFactory::Asimov
	TODO Here, we are missing some documentation. More...
class	RooStats::HistFactory::Channel
	This class encapsulates all information for the statistical interpretation of one experiment. More...
class	RooStats::HistFactory::ConfigParser
	TODO Add documentation. More...
class	RooStats::HistFactory::Data
class	RooStats::HistFactory::FlexibleInterpVar
class	RooStats::HistFactory::HistFactoryNavigation
class	RooStats::HistFactory::HistoFactor
	Configuration for an unconstrained, coherent shape variation of affected samples. More...
class	RooStats::HistFactory::HistogramUncertaintyBase
	////////////////////////////////////////////////////////////////////////////////////////////Base class to store the up and down variations for histogram uncertainties. More...
class	RooStats::HistFactory::HistoSys
	Configuration for a constrained, coherent shape variation of affected samples. More...
class	RooStats::HistFactory::HistoToWorkspaceFactoryFast
	This class provides helper functions for creating likelihood models from histograms. More...
class	RooStats::HistFactory::HistRef
	Internal class wrapping an histogram and managing its content. More...
class	RooStats::HistFactory::LinInterpVar
	RooAbsReal that does piecewise-linear interpolations. More...
class	RooStats::HistFactory::Measurement
	The RooStats::HistFactory::Measurement class can be used to construct a model by combining multiple RooStats::HistFactory::Channel objects. More...
class	RooStats::HistFactory::NormFactor
	Configuration for an un- constrained overall systematic to scale sample normalisations. More...
class	RooStats::HistFactory::OverallSys
	Configuration for a constrained overall systematic to scale sample normalisations. More...
class	ParamHistFunc
	A class which maps the current values of a RooRealVar (or a set of RooRealVars) to one of a number of RooAbsReal (nominally RooRealVar): More...
class	PiecewiseInterpolation
	The PiecewiseInterpolation is a class that can morph distributions into each other, which is useful to estimate systematic uncertainties. More...
class	RooStats::HistFactory::RooBarlowBeestonLL
	Class RooBarlowBeestonLL implements the profile likelihood estimator for a given likelihood and set of parameters of interest. More...
class	RooStats::HistFactory::Sample
class	RooStats::HistFactory::ShapeFactor
	Unconstrained bin-by-bin variation of affected histogram. More...
class	RooStats::HistFactory::ShapeSys
	Constrained bin-by-bin variation of affected histogram. More...
class	RooStats::HistFactory::StatError
	Statistical error of Monte Carlo predictions. More...
class	RooStats::HistFactory::StatErrorConfig
	Configuration to automatically assign nuisance parameters for the statistical error of the Monte Carlo simulations. More...

Functions
std::string	RooStats::HistFactory::channelNameFromPdf (RooAbsPdf *channelPdf)
void	RooStats::HistFactory::FactorizeHistFactoryPdf (const RooArgSet &, RooAbsPdf &, RooArgList &, RooArgList &)
void	RooStats::HistFactory::getDataValuesForObservables (std::map< std::string, std::vector< double > > &ChannelBinDataMap, RooAbsData data, RooAbsPdf simPdf)
int	RooStats::HistFactory::getStatUncertaintyConstraintTerm (RooArgList constraints, RooRealVar gamma_stat, RooAbsReal &pois_mean, RooRealVar &tau)
bool	RooStats::HistFactory::getStatUncertaintyFromChannel (RooAbsPdf channel, ParamHistFunc &paramfunc, RooArgList *gammaList)
RooAbsPdf *	RooStats::HistFactory::getSumPdfFromChannel (RooAbsPdf *channel)
int	main (int argc, char **argv)
	main function of the hist2workspace executable.
RooFit::OwningPtr< RooWorkspace >	RooStats::HistFactory::MakeModelAndMeasurementFast (RooStats::HistFactory::Measurement &measurement, HistoToWorkspaceFactoryFast::Configuration const &cfg={})
	Creates a statistical model and associated RooFit workspace(s) from a HistFactory measurement configuration.

Function Documentation

◆ channelNameFromPdf()

std::string RooStats::HistFactory::channelNameFromPdf ( RooAbsPdf * channelPdf )

Definition at line 25 of file HistFactoryModelUtils.cxx.

◆ FactorizeHistFactoryPdf()

void RooStats::HistFactory::FactorizeHistFactoryPdf	(	const RooArgSet &	observables,
		RooAbsPdf &	pdf,
		RooArgList &	obsTerms,
		RooArgList &	constraints )

Definition at line 73 of file HistFactoryModelUtils.cxx.

◆ getDataValuesForObservables()

void RooStats::HistFactory::getDataValuesForObservables	(	std::map< std::string, std::vector< double > > &	ChannelBinDataMap,
		RooAbsData *	data,
		RooAbsPdf *	simPdf )

Definition at line 130 of file HistFactoryModelUtils.cxx.

◆ getStatUncertaintyConstraintTerm()

int RooStats::HistFactory::getStatUncertaintyConstraintTerm	(	RooArgList *	constraints,
		RooRealVar *	gamma_stat,
		RooAbsReal *&	pois_mean,
		RooRealVar *&	tau )

Definition at line 209 of file HistFactoryModelUtils.cxx.

◆ getStatUncertaintyFromChannel()

bool RooStats::HistFactory::getStatUncertaintyFromChannel	(	RooAbsPdf *	channel,
		ParamHistFunc *&	paramfunc,
		RooArgList *	gammaList )

Definition at line 99 of file HistFactoryModelUtils.cxx.

◆ getSumPdfFromChannel()

RooAbsPdf * RooStats::HistFactory::getSumPdfFromChannel ( RooAbsPdf * channel )

Definition at line 31 of file HistFactoryModelUtils.cxx.

◆ main()

int main	(	int	argc,
		char **	argv )

main function of the hist2workspace executable.

It creates RooFit models from an xml config and files with histograms. See MakeModelAndMeasurementFast(), for further instructions.

Parameters

[in]	argc	number of CLI arguments
[in]	argv	pointer to arguments

-h Help -v Switch HistFactory message stream to INFO level. -vv Switch HistFactory message stream to DEBUG level. -disable_binned_fit_optimization Disable the binned fit optimization used in HistFactory since ROOT 6.28.

Definition at line 106 of file hist2workspace.cxx.

◆ MakeModelAndMeasurementFast()

RooFit::OwningPtr< RooWorkspace > RooStats::HistFactory::MakeModelAndMeasurementFast	(	RooStats::HistFactory::Measurement &	measurement,
		HistoToWorkspaceFactoryFast::Configuration const &	cfg = {} )

Creates a statistical model and associated RooFit workspace(s) from a HistFactory measurement configuration.

This is a package that creates a RooFit probability density function from ROOT histograms of expected distributions and histograms that represent the +/- 1 sigma variations from systematic effects. The resulting probability density function can then be used with any of the statistical tools provided within RooStats, such as the profile likelihood ratio, Feldman-Cousins, etc. In this version, the model is directly fed to a likelihood ratio test, but it needs to be further factorized.

The user needs to provide histograms (in picobarns per bin) and configure the job with XML. The configuration XML is defined in the file $ROOTSYS/config/HistFactorySchema.dtd, but essentially it is organized as follows (see the examples in ${ROOTSYS}/tutorials/roofit/histfactory/)

a top level 'Combination' that is composed of:
- several 'Channels' (eg. ee, emu, mumu), which are composed of:
  - several 'Samples' (eg. signal, bkg1, bkg2, ...), each of which has:
    - a name
    - if the sample is normalized by theory (eg N = L*sigma) or not (eg. data driven)
    - a nominal expectation histogram
    - a named 'Normalization Factor' (which can be fixed or allowed to float in a fit)
    - several 'Overall Systematics' in normalization with:
      - a name
      - +/- 1 sigma variations (eg. 1.05 and 0.95 for a 5% uncertainty)
    - several 'Histogram Systematics' in shape with:
      - a name (which can be shared with the OverallSyst if correlated)
      - +/- 1 sigma variational histograms
- several 'Measurements' (corresponding to a full fit of the model) each of which specifies
  - a name for this fit to be used in tables and files
  - what is the luminosity associated to the measurement in picobarns
  - which bins of the histogram should be used
  - what is the relative uncertainty on the luminosity
  - what is (are) the parameter(s) of interest that will be measured
  - which parameters should be fixed/floating (eg. nuisance parameters)

This function processes a RooStats::HistFactory::Measurement using the fast RooStats::HistFactory::HistoToWorkspaceFactoryFast machinery. It creates individual channel workspaces, optionally writes them to disk, and then combines them into a single RooWorkspace representing the full statistical model.