A Unified Approach to the Classical Statistical Analysis of Small Signals
read the original abstract
We give a classical confidence belt construction which unifies the treatment of upper confidence limits for null results and two-sided confidence intervals for non-null results. The unified treatment solves a problem (apparently not previously recognized) that the choice of upper limit or two-sided intervals leads to intervals which are not confidence intervals if the choice is based on the data. We apply the construction to two related problems which have recently been a battle-ground between classical and Bayesian statistics: Poisson processes with background, and Gaussian errors with a bounded physical region. In contrast with the usual classical construction for upper limits, our construction avoids unphysical confidence intervals. In contrast with some popular Bayesian intervals, our intervals eliminate conservatism (frequentist coverage greater than the stated confidence) in the Gaussian case and reduce it to a level dictated by discreteness in the Poisson case. We generalize the method in order to apply it to analysis of experiments searching for neutrino oscillations. We show that this technique both gives correct coverage and is powerful, while other classical techniques that have been used by neutrino oscillation search experiments fail one or both of these criteria.
This paper has not been read by Pith yet.
Forward citations
Cited by 17 Pith papers
-
Angular analysis of the $B^+\to\pi^+\mu^+\mu^-$ decay
First measurement of A_FB and F_H in B+→π+μ+μ− decay is consistent with Standard Model predictions in both high- and low-mass dimuon regions.
-
Many Wrongs Make a Right: Leveraging Biased Simulations Towards Unbiased Parameter Inference
Template-Adapted Mixture Model uses many biased simulations for data-driven estimates of signal and background distributions, yielding unbiased signal fraction estimates with well-calibrated uncertainties.
-
Cosmological analysis of the DESI DR1 Lyman alpha 1D power spectrum
DESI DR1 Lyman-alpha data yields Δ²★=0.379±0.032 and n★=-2.309±0.019 at k★=0.009 km⁻¹s and z=3, sharpening N_eff, α_s, and β_s constraints by factors of 1.18-1.90 when combined with other probes.
-
Little Red Dots as Hidden Neutrino Sources
Little Red Dots can contribute ~30% of the diffuse neutrino background at TeV-sub-PeV energies through photomeson production in black hole envelopes, with modified flavor ratios at higher energies.
-
From Evidence to Evident: Decisive Cosmological Evidence for the Normal Neutrino Mass Hierarchy
DESI DR2 data constrain the neutrino mass sum below the inverted hierarchy minimum, yielding Bayes factor K>460 for normal hierarchy in standard cosmology.
-
Ultra-High-Energy Cosmic Ray Boosted Relic Neutrinos
Computes the diffuse UHECR-boosted CνB flux across elastic, coherent, incoherent, resonance, and deep-inelastic channels with mixed-composition UHECR models and derives upper limits on CνB overdensity from IceCube and...
-
Stripped-Envelope Supernovae for QCD Axion Detection
Stripped-envelope supernovae enable QCD axion detection to masses around 10^{-4} eV via gamma-ray signals from conversion in progenitor magnetic fields.
-
Positron-Emitting and Electron-Capturing Double-Beta Processes in the Standard Model and Beyond
Nuclear matrix elements and phase-space factors are computed for 2ν and 0ν positron-emitting double-beta modes in three isotopes, yielding sensitivity to SMEFT lepton-number-violating operators at 1-100 TeV and showin...
-
Constraints and Projections for Millicharged Dark Matter in the Sun with Water Cherenkov Neutrino Detectors
Super-Kamiokande constrains millicharged dark matter at 5-28 GeV for fractional abundance 10^{-4.5}; Hyper-Kamiokande reaches down to 5x10^{-6}.
-
Searching for EeV photons with Telescope Array Surface Detector and neural networks
Telescope Array reports upper limits on EeV photon flux of <2.3e-3 above 10^19 eV and <3.0e-4 above 10^20 eV using a neural network classifier fine-tuned on experimental data.
-
Attenuation of the ultra-high-energy neutrino flux by dark matter scatterings
UHE neutrino flux is attenuated by DM scatterings in intergalactic and galactic media, enabling cross-section limits from events like KM3230213A under mild astrophysical assumptions.
-
GeV-scale thermal dark matter from dark photons: tightly constrained, yet allowed
In a dark-photon-mediated Dirac fermionic DM model, only narrow resonant regions with small dark-sector coupling allow the candidate to saturate the full relic density while evading current direct and indirect detecti...
-
Constraints on Neutrino Physics from DESI DR2 BAO and DR1 Full Shape
DESI DR2 BAO and full-shape data plus CMB yield ∑m_ν < 0.0642 eV (95% CL) under ΛCDM, in 3σ tension with oscillation lower limits, relaxed to <0.163 eV in w0waCDM.
-
Testing Heavy Dark Matter Decay as the Origin of KM3-230213A
Assuming the KM3-230213A event comes from heavy dark matter decay, the preferred mass exceeds 100 PeV at 95% CL with lifetimes of 10^26-10^27 s, but these regions conflict with bounds from other neutrino telescopes an...
-
Sensitivity of the As-Built Askaryan Radio Array to Ultra-High Energy Neutrinos
With 2013-2023 exposure, the as-built ARA achieves world-leading UHE neutrino sensitivity above ~10^19 eV and predicts up to 13 trigger-level events under optimistic flux models, with secondaries contributing up to 30...
-
Ultra-high energy event KM3-230213A as a cosmogenic neutrino in light of minimal UHECR flux models
Minimal UHECR flux models from the Telescope Array predict cosmogenic neutrino fluxes consistent with the KM3-230213A event at the 2σ level.
-
Deep Optical Follow-up Observations to IceCube Cosmic Neutrinos: a case for IC230724A with Subaru/HSC and prospects with Rubin/LSST
Non-detection of TDE in IC230724A; LSST could constrain TDE fraction of neutrino background to ≲60% or ≳30% with 10 events.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.