RooFitResult* | GetMinNLL() |
const RooArgSet* | fCachedBestFitParams | |
RooArgSet | fConditionalObs | conditional observables |
RooArgSet* | fDetailedOutput | ! |
bool | fDetailedOutputEnabled | |
bool | fDetailedOutputWithErrorsAndPulls | |
Bool_t | fLOffset | |
RooAbsData* | fLastData | |
RooStats::ProfileLikelihoodTestStat::LimitType | fLimitType | |
TString | fMinimizer | |
RooAbsReal* | fNll | ! |
RooAbsPdf* | fPdf | |
Int_t | fPrintLevel | |
Bool_t | fReuseNll | |
Bool_t | fSigned | |
Int_t | fStrategy | |
Double_t | fTolerance | |
TString | fVarName | |
static Bool_t | fgAlwaysReuseNll | |
static RooStats::ProfileLikelihoodTestStat::LimitType | oneSided | |
static RooStats::ProfileLikelihoodTestStat::LimitType | oneSidedDiscovery | |
static RooStats::ProfileLikelihoodTestStat::LimitType | twoSided |
interna function to evaluate test statistics can do depending on type: type = 0 standard evaluation, type = 1 find only unconditional NLL minimum, type = 2 conditional MLL
LM use default copy constructor and assignment copying the pointers. Is this what we want ?
{fLimitType = (flag ? oneSided : twoSided);}
void SetOneSidedDiscovery(Bool_t flag=true) {fOneSidedDiscovery = flag;}
{fSigned = flag;}
Main interface to evaluate the test statistic on a dataset
Returns detailed output. The value returned by this function is updated after each call to Evaluate(). The returned RooArgSet contains the following: <ul> <li> the minimum nll, fitstatus and convergence quality for each fit </li> <li> for each fit and for each non-constant parameter, the value, error and pull of the parameter are stored </li> </ul>
set the conditional observables which will be used when creating the NLL so the pdf's will not be normalized on the conditional observables when computing the NLL
{fConditionalObs.removeAll(); fConditionalObs.add(set);}