Peter Grünwald's scientific contributions

Publications (5)

Preprint
Full-text available
We study worst-case growth-rate optimal (GROW) E-variables for hypothesis testing between two group models. If the underlying group G acts freely on the observation space, there exists a maximally invariant statistic of the data. We show that among all E-statistics, invariant or not, the likelihood ratio of the maximally invariant is GROW and that...
Article
Full-text available
We introduce the problem of robust subgroup discovery , i.e., finding a set of interpretable descriptions of subsets that 1) stand out with respect to one or more target attributes, 2) are statistically robust, and 3) non-redundant. Many attempts have been made to mine either locally robust subgroups or to tackle the pattern explosion, but we are t...
Article
Science is justly admired as a cumulative process (“standing on the shoulders of giants”), yet scientific knowledge is typically built on a patchwork of research contributions without much coordination. This lack of efficiency has specifically been addressed in clinical research by recommendations for living systematic reviews and against research...
Preprint
Full-text available
A standard practice in statistical hypothesis testing is to mention the p-value alongside the accept/reject decision. We show the advantages of mentioning an e-value instead. With p-values, we cannot use an extreme observation (e.g. $p \ll \alpha$) for getting better frequentist decisions. With e-values we can, since they provide Type-I risk contro...
Preprint
Full-text available
E variables are tools for designing tests that keep their type-I error guarantees under flexible sampling scenarios such as optional stopping and continuation. We extend the recently developed E variables for two-sample tests to general null hypotheses and the corresponding anytime-valid confidence sequences. Using the 2x2 contingency table (Bernou...

Citations

... However, we would argue (following (Fisher, 1955, Edwards, 1984 and many others) that what it formalizes/idealizes is really the setting of industrial quality control rather than that of scientific inference, experimentation and accumulation of knowledge. We aim to formalize the latter instead (Ter Schure and Grünwald, 2021) -and then the BIND assumption of standard NP theory seems unrealistic; some account of dependency and optional continuation is needed, and e-values provide this. In reality the dependencies may not be as strong as in Example 2 and 3 -we adopted extreme cases there merely for illustrative purposes -but they will distort the validity of our conclusions. ...