• Corpus ID: 235436384

The Safe Logrank Test: Error Control under Continuous Monitoring with Unlimited Horizon

@inproceedings{Schure2020TheSL,
  title={The Safe Logrank Test: Error Control under Continuous Monitoring with Unlimited Horizon},
  author={Judith ter Schure and Mar{\'i}a P{\'e}rez-Ortiz and Amanda Ly and Peter D. Grunwald},
  year={2020}
}
We introduce the safe logrank test, a version of the logrank test that provides type-I error guarantees under optional stopping and optional continuation. The test is sequential without the need to specify a maximum sample size or stopping rule and allows for cumulative meta-analysis with type-I error control. The method can be extended to define anytime-valid confidence intervals. All these properties are a virtue of the recently developed martingale tests based on E-variables, of which the… 

Figures from this paper

ALL-IN meta-analysis: breathing life into living systematic reviews

The method for time-to-event data is illustrated, showing how synthesizing data at interim stages of studies can increase efficiency when studies are slow in themselves to provide the necessary number of events for completion.

Two-Sample Tests that are Safe under Optional Stopping, with an Application to Contingency Tables

Comparison to p-value analysis in simulations and a real-world example show that E-variables, through their flexibility, often allow for early stopping of data collection, thereby retaining similar power as classical methods.

ALL-IN meta-analysis: breathing life into living systematic reviews

The method for time-to-event data is illustrated, showing how synthesizing data at interim stages of studies can increase efficiency when studies are slow in themselves to provide the necessary number of events for completion.

Judith ter Schure’s contribution to the Discussion of ‘Testing by betting: A strategy for statistical and scientific communication’ by Glenn Shafer

  • J. Schure
  • Economics
    Journal of the Royal Statistical Society: Series A (Statistics in Society)
  • 2021
Professor Shafer has given a wonderful introduction into the usefulness of ‘testing by betting’ for interpreting statistical inferences. His talk provided examples of testing weather forecasters and

Safe Testing

Sharing Fisherian, Neymanian and Jeffreys-Bayesian interpretations, S-values and safe tests may provide a methodology acceptable to adherents of all three schools.

References

SHOWING 1-10 OF 41 REFERENCES

Statistical Monitoring of Clinical Trials: a Unified Approach

The title of the book, Quality Makes Money, is derived from the Ritz Carlton “profit is the residue of quality” premise and gives many samples of CQP and shows and ways to communicate these ideas from leaders to employees and vice versa.

Statistical Models Based on Counting Processes.

"Statistical Models Based on Counting Processes" may be viewed as a research monograph for mathematical statisticians and biostatisticians, although almost all methods are given in sufficient detail to be used in practice by other mathematically oriented researchers studying event histories.

Group Sequential Survival Trial Design and Monitoring Using the Log-Rank Test

A sample size formula for the two-sample log-rank test under the proportional hazards model is proposed that provides more accurate sample size calculation for unbalanced survival trial designs.

Optimal Gambling Systems for Favorable Games

The following sections are included:IntroductionThe nature of Λ*The asymptotic time minimization problemAsymptotic magnitude problemProblems with finite goals in coin tossingREFERENCES

Discussion on the paper 'Regression models and Life Tables by Sir David R

  • Cox. Journal of the Royal Statistical Society: Series B (Statistical Methodology)
  • 1972

Safe Tests and Always-Valid Confidence Intervals for contingency tables and beyond

Comparison to p-value analysis in simulations and a real-world example show that E-variables, through their flexibility, often allow for early stopping of data collection, thereby retaining similar power as classical methods.

E-values: Calibration, combination, and applications

It is demonstrated that e-values are often mathematically more tractable; in particular, in multiple testing of a single hypothesis, e- Values can be merged simply by averaging them, which allows to develop efficient procedures using e- values for testing multiple hypotheses.

Admissible anytime-valid sequential inference must rely on nonnegative martingales.

This work shows that martingales are also universal---all constructions of (composite) anytime $p-values, confidence sequences, or e-values must necessarily utilize nonnegative martingale, and provides several sophisticated examples, with special focus on the nonparametric problem of testing if a distribution is symmetric, where the new constructions render past methods inadmissible.

Likelihood, Replicability and Robbins' Confidence Sequences

The widely claimed replicability crisis in science may lead to revised standards of significance. The customary frequentist confidence intervals, calibrated through hypothetical repetitions of the

Minimum Description Length Revisited

This is an up-to-date introduction to and overview of the Minimum Description Length (MDL) Principle, a theory of inductive inference that can be applied to general problems in statistics, machine