A Paradox about Likelihood Ratios?
Data Analysis, Statistics and Probability
2017-12-13 v2 High Energy Physics - Experiment
Abstract
We consider whether the asymptotic distributions for the log-likelihood ratio test statistic are expected to be Gaussian or chi-squared. Two straightforward examples provide insight on the difference.
Cite
@article{arxiv.1711.00775,
title = {A Paradox about Likelihood Ratios?},
author = {Louis Lyons},
journal= {arXiv preprint arXiv:1711.00775},
year = {2017}
}
Comments
10 pages, no figures. Version 2 contains a new Section 4, for Gaussian probability densities (Version 1 considered only exponentials)