Comparison of chisquare variants for Poisson-distributed data and ratios
Abstract
Fits to binned, Poisson-distributed data are common in high-energy and heavy-ion physics, and they are particularly delicate in correlation function measurements, where the fitted observable is the ratio of two histograms. We compare several goodness-of-fit estimators on large toy data sets: the Neyman and Pearson χ2, their Yates continuity-corrected versions, a Neyman χ2 with the variance shifted by 1/2, the Poisson log-likelihood, and the correlation function likelihood in which both the signal and the reference histogram are treated as Poisson distributed. For a single histogram with mean occupancy λ, the Neyman χ2 underestimates the bin content by approximately one count, while the Pearson χ2 overestimates it by approximately half a count; shifting the variance by 1/2 changes the Neyman result only at order 1/λ, and only the log-likelihood recovers the mean without bias. For the ratio of two histograms, Neyman-type estimators are biased by approximately −3/λ in relative terms (3\% at λ=100), whereas the Pearson and likelihood-based fits are unbiased in the symmetric configuration studied here. The Yates correction leaves the fitted values essentially unchanged but systematically deflates the χ2, resulting in unrealistically high confidence levels. Simple analytic expressions are derived that reproduce all observed biases. Since these biases do not decrease with the number of bins, whereas the statistical uncertainties do, they can dominate the uncertainty of high-statistics, finely binned measurements. We therefore recommend likelihood-based fits, in particular the correlation function likelihood, for femtoscopic and similar ratio analyses.
Related
- Competitive constraints on exotic tensor currents from EC/β+ ratios
- All-dry processing of 3C-SiC nanomechanical string resonators for extreme aspect ratios and high intrinsic quality factor
- Exact probability distributions of complex spacing ratios in non-Hermitian random matrices
- Probing Quantum Numbers and Decay Branching Ratios of Exotic States via Entanglement-Enabled Spin Interference
- Where Chaos Pauses: Sliding-Window Frequency Ratios Reveal Transient Resonances in Relativistic Orbits
BibTeX
@misc{csanad2026comparison,
title = {{Comparison of chisquare variants for Poisson-distributed data and ratios}},
author = {Mate Csanad and Yan Huang and Daniel Kincses and Marton I. Nagy and Barnabas Porfy},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.40019},
eprint = {2609.40019},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.40019},
}
RIS
TY - UNPB
TI - Comparison of chisquare variants for Poisson-distributed data and ratios
AU - Mate Csanad
AU - Yan Huang
AU - Daniel Kincses
AU - Marton I. Nagy
AU - Barnabas Porfy
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.40019
UR - https://arxiv.org/abs/2609.40019
AB - Fits to binned, Poisson-distributed data are common in high-energy and heavy-ion physics, and they are particularly delicate in correlation function measurements, where the fitted observable is the ratio of two histograms. We compare several goodness-of-fit estimators on large toy data sets: the Neyman and Pearson χ^2, their Yates continuity-corrected versions, a Neyman χ^2 with the variance shifted by 1/2, the Poisson log-likelihood, and the correlation function likelihood in which both the signal and the reference histogram are treated as Poisson distributed. For a single histogram with mean occupancy λ, the Neyman χ^2 underestimates the bin content by approximately one count, while the Pearson χ^2 overestimates it by approximately half a count; shifting the variance by 1/2 changes the Neyman result only at order 1/λ, and only the log-likelihood recovers the mean without bias. For the ratio of two histograms, Neyman-type estimators are biased by approximately −3/λ in relative terms (3\% at λ=100), whereas the Pearson and likelihood-based fits are unbiased in the symmetric configuration studied here. The Yates correction leaves the fitted values essentially unchanged but systematically deflates the χ^2, resulting in unrealistically high confidence levels. Simple analytic expressions are derived that reproduce all observed biases. Since these biases do not decrease with the number of bins, whereas the statistical uncertainties do, they can dominate the uncertainty of high-statistics, finely binned measurements. We therefore recommend likelihood-based fits, in particular the correlation function likelihood, for femtoscopic and similar ratio analyses.
ER -