English

Bootstrap-determined p-values in Lattice QCD

High Energy Physics - Lattice 2024-09-18 v1

Abstract

We present a general method to determine the probability that stochastic Monte Carlo data, in particular those generated in a lattice QCD calculation, would have been obtained were that data drawn from the distribution predicted by a given theoretical hypothesis. Such a probability, or p-value, is often used as an important heuristic measure of the validity of that hypothesis. The proposed method offers the benefit that it remains usable in cases where the standard Hotelling T2T^2 methods based on the conventional χ2\chi^2 statistic do not apply, such as for uncorrelated fits. Specifically, we analyze a general alternative to the correlated χ2\chi^2 statistic referred to as q2q^2, and show how to use the bootstrap as a data-driven method to determine the expected distribution of q2q^2 for a given hypothesis with minimal assumptions. This distribution can then be used to determine the p-value for a fit to the data. We also describe a bootstrap approach for quantifying the impact upon this p-value of estimating population parameters from a single ensemble of NN samples. The overall method is accurate up to a 1/N1/N bias which we do not attempt to quantify.

Keywords

Cite

@article{arxiv.2409.11379,
  title  = {Bootstrap-determined p-values in Lattice QCD},
  author = {Norman Christ and Rajiv Eranki and Christopher Kelly},
  journal= {arXiv preprint arXiv:2409.11379},
  year   = {2024}
}

Comments

46 pages, 22 figures

R2 v1 2026-06-28T18:48:07.122Z