Cargando…

Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform

The interpretation of new particle search results involves a confidence level calculation on either the discovery hypothesis or the background-only ("null") hypothesis. A typical approach uses toy Monte Carlo experiments to build an expected experiment estimator distribution against which...

Descripción completa

Detalles Bibliográficos
Autores principales: Hu, H, Nielsen, J
Lenguaje:eng
Publicado: CERN 1999
Materias:
Acceso en línea:https://dx.doi.org/10.5170/CERN-2000-005.109
http://cds.cern.ch/record/389410
_version_ 1780893669811814400
author Hu, H
Nielsen, J
author_facet Hu, H
Nielsen, J
author_sort Hu, H
collection CERN
description The interpretation of new particle search results involves a confidence level calculation on either the discovery hypothesis or the background-only ("null") hypothesis. A typical approach uses toy Monte Carlo experiments to build an expected experiment estimator distribution against which an observed experiment's estimator may be compared. In this note, a new approach is presented which calculates analytically the experiment estimator distribution via a Fourier transform, using the likelihood ratio as an ordering estimator. The analytic approach enjoys an enormous speed advantage over the toy Monte Carlo method, making it possible to quickly and precisely calculate confidence level results.
id cern-389410
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 1999
publisher CERN
record_format invenio
spelling cern-3894102019-09-30T06:29:59Zdoi:10.5170/CERN-2000-005.109http://cds.cern.ch/record/389410engHu, HNielsen, JAnalytic Confidence Level Calculations using the Likelihood Ratio and Fourier TransformDetectors and Experimental TechniquesThe interpretation of new particle search results involves a confidence level calculation on either the discovery hypothesis or the background-only ("null") hypothesis. A typical approach uses toy Monte Carlo experiments to build an expected experiment estimator distribution against which an observed experiment's estimator may be compared. In this note, a new approach is presented which calculates analytically the experiment estimator distribution via a Fourier transform, using the likelihood ratio as an ordering estimator. The analytic approach enjoys an enormous speed advantage over the toy Monte Carlo method, making it possible to quickly and precisely calculate confidence level results.CERNphysics/9906010WISC-EX-99-352oai:cds.cern.ch:3894101999-06-07
spellingShingle Detectors and Experimental Techniques
Hu, H
Nielsen, J
Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title_full Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title_fullStr Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title_full_unstemmed Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title_short Analytic Confidence Level Calculations using the Likelihood Ratio and Fourier Transform
title_sort analytic confidence level calculations using the likelihood ratio and fourier transform
topic Detectors and Experimental Techniques
url https://dx.doi.org/10.5170/CERN-2000-005.109
http://cds.cern.ch/record/389410
work_keys_str_mv AT huh analyticconfidencelevelcalculationsusingthelikelihoodratioandfouriertransform
AT nielsenj analyticconfidencelevelcalculationsusingthelikelihoodratioandfouriertransform