Pith. sign in

REVIEW 20 cited by

Hypothesis testing with e-values

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.23614 v6 pith:OIUVU4ZK submitted 2024-10-31 math.ST stat.MEstat.TH

classification math.STstat.MEstat.TH
keywords e-valueschaptersconceptsparttestingadvancedbookcontains
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This book is written to offer a humble, but unified, treatment of e-values in hypothesis testing. It is organized into three parts: Fundamental Concepts, Core Ideas, and Advanced Topics. The first part includes four chapters that introduce the basic concepts. The second part includes five chapters of core ideas such as universal inference, log-optimality, e-processes, operations on e-values, and e-values in multiple testing. The third part contains seven chapters of advanced topics. The book collates important results from a variety of modern papers on e-values and related concepts, and also contains many results not published elsewhere. It offers a coherent and comprehensive picture on a fast-growing research area, and is ready to use as the basis of a graduate course in statistics and related fields.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A mathematical study of the excess growth rate

    cs.IT 2025-10 conditional novelty 7.0 of 10

    The excess growth rate is the unique functional, up to a constant, satisfying each of three axiom systems; its deterministic maximizer invests only in the best- and worst-performing assets.

  2. The e-Partitioning Principle of False Discovery Rate Control

    math.ST 2025-04 conditional novelty 7.0 of 10

    The e-Partitioning Principle states that a procedure controls FDR if and only if it is a subset of a general e-value based partitioning procedure, yielding uniform improvements of eBH, BY and Su.

  3. Mean Estimation in Banach Spaces Under Infinite Variance and Martingale Dependence

    math.ST 2024-11 conditional novelty 7.0 of 10

    A truncation-based estimator achieves the optimal heavy-tailed mean estimation rate in smooth Banach spaces under martingale dependence with time-uniform guarantees.

  4. Assessing Extrapolation of Peaks Over Thresholds with Martingale Testing

    stat.ME 2025-12 conditional novelty 6.0 of 10

    A gambling-style test over the largest observed rainfalls selects the extreme-value threshold that won the EVA2025 challenge — except on one target, where the authors overrode the game and paid for it.

  5. E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing

    cs.LG 2025-12 conditional novelty 6.0 of 10

    A density-ratio e-process wrapper converts black-box verifier scores into sequential decisions that control the false-alarm rate for agent trajectories, with empirical gains in early stopping.

  6. Hypothesis Testing in Imaging Inverse Problems

    stat.ML 2025-05 conditional novelty 6.0 of 10

    Semantic hypotheses about reconstructed images are tested using CLIP embeddings and e-values, with calibrated Type I error control and higher power than zero-shot CLIP classification.

  7. On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds

    math.ST 2025-04 conditional novelty 6.0 of 10

    For arbitrary composite nulls and alternatives, any power-one sequential test needs at least log(1/alpha)/KL_inf samples when alpha is small, and at least a law-of-iterated-logarithm scale when the alternative is clos...

  8. Uniform mean estimation for monotonic processes

    math.ST 2025-02 conditional novelty 6.0 of 10

    Coin-betting plus a monotonicity-based continuous union bound yields uniform, anytime-valid, variance-adaptive confidence bands for monotonic mean functions such as CDFs.

  9. Carefree multiple testing with e-processes

    math.ST 2025-01 conditional novelty 6.0 of 10

    Running-maximum e-BH can exceed the nominal FDR under arbitrary dependence, while adjusted running maxima restore FDR-sup control.

  10. Calibrating Wireless AI via Meta-Learned Context-Dependent Conformal Prediction

    eess.SP 2025-01 conditional novelty 6.0 of 10

    ML-WCP meta-learns a context-dependent likelihood ratio and uses it inside weighted conformal prediction to calibrate wireless AI with zero runtime data.

  11. Optimal e-value testing for properly constrained hypotheses

    math.ST 2024-12 accept novelty 6.0 of 10

    For a hypothesis given by finitely many continuous moment constraints with the origin in the relative interior of the feasible convex hull, the optimal e-variable set is the dual class {1 - λ·Φ : λ ∈ Λ_Φ}.

  12. Hypothesis testing for community structure in temporal networks using e-values

    stat.ME 2025-07 conditional novelty 5.0 of 10

    A temporal-network community test averages e-values obtained from per-snapshot p-values, retaining valid type I error control under arbitrary dependence.

  13. Optimistic Interior Point Methods for Sequential Hypothesis Testing by Betting

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A new 'test by betting' algorithm using interior-point barrier updates over the full decision domain rejects false null hypotheses faster than Online Newton Step while preserving anytime validity.

  14. On Continuous Monitoring of Risk Violations under Unknown Shift

    stat.ML 2025-06 conditional novelty 4.0 of 10

    A betting-based wealth process monitors whether a deployed predictor's bounded risk has crossed a safety level, raising a controlled-false-alarm signal under unknown distribution shift and a set of thresholds still co...

  15. Randomness, exchangeability, and conformal prediction

    cs.LG 2025-01 conditional novelty 4.0 of 10

    In classification, every confidence predictor that is valid under IID data can be transformed into a conformal predictor with an explicit, constant-free bound on the loss of efficiency.

  16. My Statistics is Better than Yours

    stat.OT 2024-12 conditional novelty 4.0 of 10

    A position paper advocating a context-dependent choice of statistical paradigm instead of a universal one.

  17. Multiple Testing in Generalized Universal Inference

    stat.ME 2024-12 conditional novelty 4.0 of 10

    Generalized universal inference e-values can be plugged into e-BH to control FDR for multiple tests on risk minimizers, with a quantile regression application.

  18. Ensuring Reliability via Hyperparameter Selection: Review and Advances

    cs.LG 2025-02 conditional novelty 2.0 of 10

    The paper reviews methods that cast hyperparameter selection as multiple hypothesis testing to deliver formal risk guarantees.

  19. Measuring Statistical Evidence: A Short Report

    stat.ME 2024-11 unverdicted novelty 2.0 of 10

    A report summarizing and motivating the Relative Belief Ratio framework for statistical evidence, adding one unproven modification to strength-of-evidence measurement.

  20. False Discovery Control in Multiple Testing: A Brief Overview of Theories and Methodologies

    stat.ME 2024-11 accept novelty 2.0 of 10

    This is a survey of false discovery rate control methods, organized into ranking, FDP estimation, and thresholding steps.

Pith tools