Uncertainty components in profile likelihood fits (2307.04007v4)
Abstract: When a measurement of a physical quantity is reported, the total uncertainty is usually decomposed into statistical and systematic uncertainties. This decomposition is not only useful to understand the contributions to the total uncertainty, but also required to propagate these contributions in subsequent analyses, such as combinations or interpretation fits including results from other measurements or experiments. In profile-likelihood fits, widely applied in high-energy physics analyses, contributions of systematic uncertainties are routinely quantified using "impacts", which are not adequate for such applications. We discuss the difference between impacts and actual uncertainty components, and establish methods to determine the latter in a wide range of statistical models.
- DOI 10.1140/epjc/s10052-012-1874-8. [Erratum: Eur.Phys.J.C 72, 1874 (2012)]
- DOI 10.5506/APhysPolB.53.12-A1
- DOI 10.1016/j.physrep.2005.12.006
- DOI 10.1140/epjc/s10052-023-11587-8
- DOI 10.1007/JHEP08(2016)045
- DOI 10.1016/0168-9002(88)90018-6
- DOI 10.1016/S0168-9002(03)00329-2
- DOI 10.1016/j.nima.2005.05.068
- DOI 10.1016/j.physrep.2013.07.004
- BABAR Analysis Document 318 (2002). URL https://babar.heprc.uvic.ca/BFROOT/www/Statistics/Report/report.pdf
- DOI 10.1017/S0080456800012163
- DOI 10.1017/S0021859600003750
- DOI 10.1016/j.physletb.2018.07.050
- DOI https://doi.org/10.1002/9783527653416.ch2. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/9783527653416.ch2
- DOI 10.1088/0954-3899/37/7A/075021
- DOI 10.1140/epjc/s10052-012-2041-y
- DOI 10.1088/0031-8949/51/6/002
- DOI 10.1140/epjc/s10052-022-10581-w
- L. Demortier, Equivalence of the best-fit and covariance-matrix methods for comparing binned data with a model in the presence of correlated systematic uncertainties. CDF Note 8661 (1999). URL https://www-cdf.fnal.gov/physics/statistics/notes/cdf8661_chi2fit_w_corr_syst.pdf
- DOI 10.1103/PhysRevD.66.053010
- DOI 10.1103/PhysRevD.65.014012
- DOI 10.1088/0954-3899/28/10/314
- DOI 10.1088/0954-3899/28/5/305
- DOI 10.1063/1.2122026
- DOI 10.1016/j.nima.2020.164864
- B. List. Decomposition of a covariance matrix into uncorrelated and correlated errors. https://indico.desy.de/event/3009/contributions/64704/ (2010). Alliance Workshop on Unfolding and Data Correction, DESY
- DOI 10.1007/JHEP05(2014)059
- DOI 10.1007/978-1-4612-4380-9_41. URL https://doi.org/10.1007/978-1-4612-4380-9_41
- DOI 10.1016/j.physletb.2020.135425
- DOI 10.1103/PhysRevLett.108.151804
- DOI 10.1140/epjc/s10052-017-5475-4. [Erratum: Eur.Phys.J.C 78, 898 (2018)]
- DOI 10.1007/JHEP01(2022)036
- DOI 10.1126/science.abk1781
- DOI 10.1103/PhysRevLett.25.316. URL https://link.aps.org/doi/10.1103/PhysRevLett.25.316
- DOI 10.1007/JHEP07(2014)079
- DOI 10.1016/j.cpc.2008.01.036
- DOI https://doi.org/10.1016/0370-2693(88)91627-9. URL https://www.sciencedirect.com/science/article/pii/0370269388916279
- Tech. rep., New York U., New York (2012). URL https://cds.cern.ch/record/1456844
- URL http://inspirehep.net/record/634021. [eConf C0303241, MOLT007]
- DOI 10.1140/epjc/s10052-017-5345-0
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.