Statistical Formulas for F Measures
arXiv:2012.14894v12 citations
AI Analysis
This work addresses the problem of accurately estimating F-measures for researchers and practitioners who rely on these metrics for model evaluation, offering an incremental improvement in statistical rigor.
This paper provides analytical formulas for the standard error and confidence intervals of F-measures. These formulas can be used for sample size planning to ensure accurate estimation of F-measures.
We provide analytic formulas for the standard error and confidence intervals for the F measures, based on a property of asymptotic normality in the large sample limit. The formula can be applied for sample size planning in order to achieve accurate enough estimation of these F measures.