StanCon 2026 will take place 17–21 August 2026 in Uppsala, Sweden - details at https://stancon2026.org First Keynote Confirmed Speaker Anna Dreber (Stockholm School of Economics) (Predicting) replic...

Hi everyone! Registration for StanCon 2026 in Uppsala, Sweden, is now open! You can already register and submit abstracts for contributions. Our first keynote speaker will be announced soon. New thi...

Hi everyone! Registration for StanCon 2026 in Uppsala, Sweden, is now open! You can already register and submit abstracts for contributions. Our first keynote speaker will be announced soon. New thi...

Website of the Uppsala University Information Laboratory.

Holli Sargeant, Andreas Östling, Måns Magnusson. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

It is useful to estimate the expected predictive performance of models planned to be used for prediction. We focus on leave-one-out cross-validation (LOO-CV), which has become a popular method for estimating predictive performance of Bayesian models. Given two models, we are interested in comparing the predictive performances and associated uncertainty, which can also be used to compute the probability of one model having better predictive performance than the other model. We study the properties of the Bayesian LOO-CV estimator and the related uncertainty quantification for the predictive performance difference, and analyse when a normal approximation of this uncertainty is well calibrated and whether taking into account higher moments could improve the approximation. We provide new results of the properties both theoretically in the linear regression case and empirically for hierarchical linear, latent linear, and spline models and discuss the challenges. We show that problematic cases include: comparing models with similar predictions, misspecified models, and small data. In these cases, there is a weak connection between the distributions of the LOO-CV estimator and its error. We show that that the problematic skewness of the error distribution for the difference, which occurs when the models make similar predictions, does not fade away when the data size grows to infinity in certain situations. Based on the results, we also provide some practical recommendations for the users of Bayesian LOO-CV for comparing predictive performance of models.

Säljer solrosor för Ukraina – Drar in tusentals kronor

Algorithmic discrimination is a critical concern as machine learning models are used in high-stakes decision-making in legally protected contexts. Although substantial research on algorithmic bias and...

Hi everyone, Good news on posteriordb! We (@Bob_Carpenter , @paul.buerkner , @avehtari @Lu.Zhang and @Jakob_Torgander and me) have now published a paper on posteriordb at AISTATs. The paper can be f...

As an international student, I am well aware that the opinions I express carry a certain degree of risk. Still, I refuse to remain silent. Citizens or not, we all have agency over the direction this c...

This years winner of the Cramér prize for best doctoral thesis in statistics/mathematical statistics is Johan Larsson (LU), with his thesis Optimizatio ...