• Corpus ID: 229717721

Merging sequential e-values via martingales

@inproceedings{Vovk2020MergingSE,
  title={Merging sequential e-values via martingales},
  author={Vladimir Vovk and Ruodu Wang},
  year={2020}
}
We study the problem of merging sequential or independent e-values into one e-value for statistical decision making. We describe a class of e-value merging functions via martingales, and show that all merging methods for sequential e-values are dominated by such a class. In case of merging independent e-values, the situation becomes much more sophis-ticated, and we provide a general class of such merging functions based on reordered test martingales. 
1 Citations

Figures from this paper

E-backtesting

In the recent Basel Accords, the Expected Shortfall (ES) replaces the Value-at-Risk (VaR) as the standard risk measure for market risk in the banking sector, making it the most important risk measure

References

SHOWING 1-10 OF 24 REFERENCES

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.

Test Martingales, Bayes Factors and p-Values

A nonnegative martingale with initial value equal to one measures evidence against a probabilistic hypothesis. The inverse of its value at some stopping time can be interpreted as a Bayes factor. If

E-values as unnormalized weights in multiple testing

This work shows that standard weighted multiple testing methods are not required when the weights are not constants, but are themselves e-values obtained from independent data, which could result in a massive increase in power.

Combining P-Values Via Averaging

This paper proposes general methods for the problem of multiple testing of a single hypothesis, with a standard goal of combining a number of $p$-values without making any assumptions about their

Extreme negative dependence and risk aggregation

  • Bin WangRuodu Wang
  • Mathematics, Computer Science
    J. Multivar. Anal.
  • 2015

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.

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.

Testing by betting: A strategy for statistical and scientific communication

  • G. Shafer
  • Computer Science
    Journal of the Royal Statistical Society: Series A (Statistics in Society)
  • 2021
A simpler way of reporting statistical evidence is introduced: report the outcome of a bet against the null hypothesis, which leads to a new role for likelihood, to alternatives to power and confidence, and to a framework for meta‐analysis that accommodates both planned and opportunistic testing of statistical hypotheses and probabilistic forecasts.

On Tables of Random Numbers

The editors of Semiotika i Informatika have felt it appropriate to publish a Russian translation of my article, which reflects a certain stage of my attempts to give meaning to the frequency

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.