Research output per year
Research output per year
Abstract
We develop the theory of hypothesis testing based on the e-value, a notion of evidence
that, unlike the p-value, allows for effortlessly combining results from several studies in the
common scenario where the decision to perform a new study may depend on previous out-
comes. Tests based on e-values are safe, i.e. they preserve Type-I error guarantees, under
such optional continuation. We define growth-rate optimality (GRO) as an analogue of
power in an optional continuation context, and we show how to construct GRO e-variables
for general testing problems with composite null and alternative, emphasizing models with
nuisance parameters. GRO e-values take the form of Bayes factors with special priors.
We illustrate the theory using several classic examples including a one-sample safe t-test
and the 2 × 2 contingency table. Sharing Fisherian, Neymanian and Jeffreys-Bayesian
interpretations, e-values may provide a methodology acceptable to adherents of all three
schools.
that, unlike the p-value, allows for effortlessly combining results from several studies in the
common scenario where the decision to perform a new study may depend on previous out-
comes. Tests based on e-values are safe, i.e. they preserve Type-I error guarantees, under
such optional continuation. We define growth-rate optimality (GRO) as an analogue of
power in an optional continuation context, and we show how to construct GRO e-variables
for general testing problems with composite null and alternative, emphasizing models with
nuisance parameters. GRO e-values take the form of Bayes factors with special priors.
We illustrate the theory using several classic examples including a one-sample safe t-test
and the 2 × 2 contingency table. Sharing Fisherian, Neymanian and Jeffreys-Bayesian
interpretations, e-values may provide a methodology acceptable to adherents of all three
schools.
| Original language | English |
|---|---|
| Title of host publication | 2020 Information Theory and Applications Workshop (ITA) |
| Subtitle of host publication | [Proceedings] |
| Publisher | IEEE |
| Number of pages | 47 |
| ISBN (Electronic) | 9781728141909 |
| ISBN (Print) | 9781728188256 |
| DOIs | |
| Publication status | Published - 2020 |
Fingerprint
Dive into the research topics of 'Safe Testing'. Together they form a unique fingerprint.-
Safe testing
Grünwald, P., de Heide, R. & Koolen, W., Nov 2024, In: Journal of the Royal Statistical Society. Series B: Statistical Methodology. 86, 5, p. 1091-1128 38 p.Research output: Contribution to Journal › Article › Academic › peer-review
-
Safe Testing
Grunwald, P., De Heide, R. & Koolen, W. M., 10 Mar 2023, arXiv, p. 1-47, 47 p.Research output: Working paper / Preprint › Preprint › Academic
Open Access