7 papers · 1 filter
Bentkus-type asymptotic e-values
Diego Martinez-Taboada, Ben Chugg, Aaditya Ramdas
Asymptotic e-values are emerging as a powerful alternative to asymptotic p-values, particularly in post-hoc inference and multiple testing, where significance levels may be data-de…
Post-Hoc Large-Sample Statistical Inference
Ben Chugg, Etienne Gauthier, Michael I. Jordan +2
We derive inferential procedures for large sample sizes that remain valid under data-dependent significance levels (so-called "post-hoc valid inference"). Classical statistical too…
On admissibility in post-hoc hypothesis testing
Ben Chugg, Tyron Lardy, Aaditya Ramdas +1
The validity of classical hypothesis testing requires the significance level be fixed before any statistical analysis takes place. This is a stringent requirement. For instanc…
Closed-form empirical Bernstein confidence sequences for scalars and matrices
Ben Chugg, Aaditya Ramdas
We derive a new closed-form variance-adaptive confidence sequence (CS) for estimating the average conditional mean of a sequence of bounded random variables. Empirically, it yields…
Rao-Blackwellized e-variables
Dante de Roos, Ben Chugg, Peter Grünwald +1
We show that for any concave utility, the expected utility of an e-variable can only increase after conditioning on a sufficient statistic. The simplest form of the result has an e…
Time-Uniform Confidence Spheres for Means of Random Vectors
Ben Chugg, Hongjian Wang, Aaditya Ramdas
We study sequential mean estimation in . In particular, we derive time-uniform confidence spheres -- confidence sphere sequences (CSSs) -- which contain the mean of r…