A new model test in high energy physics in frequentist and Bayesian statistical formalisms

Abstract

A problem of a new physical model test given observed experimental data is a typical one for modern experiments of high energy physics (HEP). A solution of the problem may be provided with two alternative statistical formalisms, namely frequentist and Bayesian, which are widely spread in contemporary HEP searches. A characteristic experimental situation is modeled from general considerations and both the approaches are utilized in order to test a new model. The results are juxtaposed, what demonstrates their consistency in this work. An effect of a systematic uncertainty treatment in the statistical analysis is also considered.

References in corpus (5)

• Asymptotic formulae for likelihood-based tests of new physics
• Bayes in the sky: Bayesian inference and model selection in cosmology
• HistFitter software framework for statistical data analysis
• The RooFit toolkit for data modeling
• The RooStats Project