Colloquium - Sara Algeri - November 6, 2025

Speaker: Sara Algeri, University of Minnesota
Date/Time: Thursday, November 6, 2025, 10:00 AM - 11:00 AM ET

Title: When Pearson's Chi-square and other divisible statistics are not goodness-of-fit tests

Abstract: This talk introduces a unifying approach to the analysis of grouped data, which allows us to study the class of divisible statistics  --  that includes Pearson's Chi-square, the likelihood ratio as special cases  --  from a new perspective. Such a study reveals that no single divisible statistic is adequate for goodness-of-fit.

It also shows that, in a sparse regime, all tests proposed in the literature are dominated by a class of weighted linear statistics. The construction of goodness-of-fit distribution-free tests is also discussed.

Bio: Sara Algeri is an Associate Professor in the School of Statistics at the University of Minnesota. Her research interests mainly lie in astrostatistics, statistical inference, and goodness-of-fit. The main purpose of her work is to provide highly generalizable statistical solutions that directly address fundamental questions in the physical sciences, and can at the same time be easily applied to any other scientific problem following a similar statistical paradigm. In line with this, motivated by problems arising in high-energy physics and astronomy, her current research focuses on statistical inference for signal detection, background uncertainty quantification, and model validation.

Website: https://salgeri.umn.edu/