Statistical unfolding of elementary particle spectra: empirical Bayes estimation and bias-corrected uncertainty quantification

DOI10.1214/15-AOAS857zbMATH Open1454.62533arXiv1505.04768OpenAlexW2116545726MaRDI QIDQ902940FDOQ902940

Authors: Mikael Kuusela, Victor M. Panaretos 

Publication date: 4 January 2016

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: We consider the high energy physics unfolding problem where the goal is to estimate the spectrum of elementary particles given observations distorted by the limited resolution of a particle detector. This important statistical inverse problem arising in data analysis at the Large Hadron Collider at CERN consists in estimating the intensity function of an indirectly observed Poisson point process. Unfolding typically proceeds in two steps: one first produces a regularized point estimate of the unknown intensity and then uses the variability of this estimator to form frequentist confidence intervals that quantify the uncertainty of the solution. In this paper, we propose forming the point estimate using empirical Bayes estimation which enables a data-driven choice of the regularization strength through marginal maximum likelihood estimation. Observing that neither Bayesian credible intervals nor standard bootstrap confidence intervals succeed in achieving good frequentist coverage in this problem due to the inherent bias of the regularized point estimate, we introduce an iteratively bias-corrected bootstrap technique for constructing improved confidence intervals. We show using simulations that this enables us to achieve nearly nominal frequentist coverage with only a modest increase in interval length. The proposed methodology is applied to unfolding the $Z$ boson invariant mass spectrum as measured in the CMS experiment at the Large Hadron Collider.

Full work available at URL: https://arxiv.org/abs/1505.04768

Recommendations

• Shape-constrained uncertainty quantification in unfolding steeply falling elementary particle spectra
• scientific article; zbMATH DE number 1203819
• Convergence and error propagation results on a linear iterative unfolding method
• Statistical methods for data analysis in particle physics
• Quasi-maximum likelihood estimation of parameters in a multivariate Poisson process

zbMATH Keywords

bootstrapregularizationPoisson processhigh energy physicsMonte Carlo EM algorithmLarge Hadron ColliderPoisson inverse problem

Mathematics Subject Classification ID

Applications of statistics to physics (62P35)

Cites Work

• Semiparametric Regression
• Title not available (Why is that?)
• Flexible smoothing with \(B\)-splines and penalties. With comments and a rejoinder by the authors
• Title not available (Why is that?)
• Title not available (Why is that?)
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• Gaussian processes for machine learning.
• ON CONFIDENCE INTERVALS FOR GENERALIZED ADDITIVE MODELS BASED ON PENALIZED REGRESSION SPLINES
• Title not available (Why is that?)
• Pattern recognition and machine learning.
• A practical guide to splines.
• Statistical and computational inverse problems.
• The EM Algorithm and Extensions, 2E
• Title not available (Why is that?)
• Title not available (Why is that?)
• Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)
• Title not available (Why is that?)
• Maximizing Generalized Linear Mixed Model Likelihoods With an Automated Monte Carlo EM Algorithm
• A statistical perspective on ill-posed inverse problems (with discussion)
• Bayesian methods for data analysis.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Aristotelian prior boundary conditions
• Title not available (Why is that?)
• Consistency of the posterior distribution in generalized linear inverse problems
• Deconvolution problems in nonparametric statistics
• Title not available (Why is that?)
• Spatially adaptive smoothing splines
• A course on point processes
• Fast Computation of Fully Automated Log-Density and Log-Hazard Estimators
• Regularization parameter selection methods for ill-posed Poisson maximum likelihood estimation
• A Statistical Model for Positron Emission Tomography
• Poisson inverse problems
• Fully Bayesian Reconstructions From Single-Photon Emission Computed Tomography Data
• Title not available (Why is that?)
• Splines with Nonnegative B-Spline Coefficients
• Efficient Derivative Codes through Automatic Differentiation and Interface Contraction: An Application in Biostatistics
• Statistical unfolding of elementary particle spectra: empirical Bayes estimation and bias-corrected uncertainty quantification

Cited In (8)

• Post hoc Uncertainty Quantification for Remote Sensing Observing Systems
• Objective frequentist uncertainty quantification for atmospheric \(\text{CO}_2\) retrievals
• Towards Improved Heliosphere Sky Map Estimation with Theseus
• Statistical unfolding of elementary particle spectra: empirical Bayes estimation and bias-corrected uncertainty quantification
• Bayesian inference of the fluctuating proton shape
• Shape-constrained uncertainty quantification in unfolding steeply falling elementary particle spectra
• Data unfolding with mean integrated square error optimization
• Convergence and error propagation results on a linear iterative unfolding method

Uses Software

• SemiPar
• bootstrap
• bootlib
• PRMLT

This page was built for publication: Statistical unfolding of elementary particle spectra: empirical Bayes estimation and bias-corrected uncertainty quantification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q902940)