1 / 7

Current Statistical Issues in Particle Physics

This document presents an overview of current statistical challenges in particle physics as discussed by Louis Lyons at the PHYSTAT conferences. It covers fundamental aspects of particle physics, the nature of data involved, typical analysis methods, and specific experimental results from LEP, BaBar/Belle, and the LHC. The importance of robust statistical techniques, including multivariate analysis and likelihood fits, is emphasized, alongside the need for help with background concerns and parameter estimation. The talk also highlights future directions for statistical theory in the field.

sugar
Télécharger la présentation

Current Statistical Issues in Particle Physics

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Current Statistical Issues in Particle Physics Louis Lyons Particle Physics Oxford U.K. Future of Statistical Theory HyderabadDecember 2004

  2. Current Statistical Issues in Particle Physics • What is Particle Physics? • What is Particle Physics data like? • Typical analysis • PHYSTAT Conferences • Where we would like help

  3. Typical Experiments • Experiment Energy Beams # events Result • LEP 200 GeV e+ e- 10 Z N = 2.987± 0.008 • BaBar/Belle 10 GeV e+ e- 10 BB CP-violation • Tevatron 2000 GeV p anti-p “1014” SUSY? • LHC 14000 GeV p p (2007…) Higgs? • Super-K ~3 GeV KK 100 ν oscillations

  4. CDF at Fermilab

  5. TypicalAnalysis • Parameter determination: dn/dt = 1/τ * exp(-t/ τ) Worry about backgrounds, t resolution, t-dependent efficiency • 1) Reconstruct tracks • 2) Select real events • 3) Select wanted events • 4) Extract t from L and v • 5) Model signal and background • 6) Likelihood fit for lifetime and statistical error • 7) Estimate systematic error τ± στ(stat)± στ(syst)

  6. Where we would like help Access to understood programs Multivariate analysis Cuts, Fisher, PCA, NN, SVM, Boosted Trees……. Confidence limits Nuisance parameters Unphysical values Coverage? Very small intervals Estimating signal significance S/ B Nuisance parameters Look elsewhere effect Goodness of fit Sparse multi-dimensional data Combining results Asymmetric errors Overlapping data samples

More Related