SubsidieMeestersFlexible Statistical Inference
Develop a flexible statistical theory allowing post-hoc data collection and decision-making with error control, utilizing e-values for improved inference in small samples.
Projectdetails
Introduction
Most statistical methods require that all aspects of data collection and inference are determined in advance, independently of the data. These include when to stop collecting data, what decisions can be made (e.g., accept/reject hypothesis, classify new point), and how to measure their quality (e.g., loss function/significance level). This is wildly at odds with the flexibility required in practice! It makes it impossible to achieve error control in meta-analyses and contributes to the replication crisis in the applied sciences.
Project Overview
I will develop a novel statistical theory in which all data-collection and decision aspects may be unknown in advance, possibly imposed post-hoc, depending on the data itself in unknowable ways. Yet this new theory will provide small-sample frequentist error control, risk bounds, and confidence sets.
Theoretical Foundations
I base myself on far-reaching extensions of e-values/processes. These generalize likelihood ratios and replace p-values, capturing 'evidence' in a much cleaner fashion. As lead author of the first paper (2019) that gave e-values a name and demonstrated their enormous potential, I kicked off and then played an essential role in the extremely rapid development of anytime-valid inference, the one aspect of flexibility that is by now well-studied.
Research Goals
Still, efficient e-value design principles for many standard problems (e.g., GLMs and other settings with covariates) are still lacking, and I will provide them. I will also develop theory for full decision-task flexibility, about which currently almost nothing is known. A major innovation is the e-posterior, which behaves differently from the Bayesian one: if priors are chosen badly, e-posterior based confidence intervals get wide rather than wrong.
Implications of the New Theory
Both the existing Wald-Neyman-Pearson and Bayesian statistical theories will arise as special, extreme cases of the new theory, based on perfect (hence unrealistic) knowledge of the data-collection/decision problem or the underlying distribution(s), respectively.
Financiële details & Tijdlijn
Financiële details
| Subsidiebedrag | € 2.499.461 |
| Totale projectbegroting | € 2.499.461 |
Tijdlijn
| Startdatum | 1-11-2024 |
| Einddatum | 31-10-2029 |
| Subsidiejaar | 2024 |
Partners & Locaties
Projectpartners
- STICHTING NEDERLANDSE WETENSCHAPPELIJK ONDERZOEK INSTITUTENpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Assumption-Lean (Causal) Modelling and Estimation: A Paradigm Shift from Traditional Statistical ModellingDevelop a flexible 'assumption-lean modelling' framework for causal inference that minimizes bias and enhances interpretability in statistical analyses using debiased learning techniques. | ERC Advanced... | € 2.445.063 | 2024 | Details |
The missing mathematical story of Bayesian uncertainty quantification for big dataThis project aims to enhance scalable Bayesian methods through theoretical insights, improving their accuracy and acceptance in real-world applications like medicine and cosmology. | ERC Starting... | € 1.492.750 | 2022 | Details |
Information Economics With Fundamental Uncertainty: Robustness, Commitment, and Strategic IncentivesThis project explores how fundamental uncertainty affects learning and strategic information sharing, using decision-theoretic frameworks to enhance understanding of active experimentation and information dynamics. | ERC Starting... | € 1.402.678 | 2025 | Details |
Statistical theory and methodology for the combination of heterogeneous and distributed dataDevelop new statistical methodologies to address data heterogeneity and measurement errors across diverse datasets, enhancing evidence-based advancements in science and policy. | ERC Starting... | € 1.499.689 | 2024 | Details |
Uniting Statistical Testing and Machine Learning for Safe PredictionsThe project aims to enhance the interpretability and reliability of machine learning predictions by integrating statistical methods to establish robust error bounds and ensure safe deployment in real-world applications. | ERC Starting... | € 1.500.000 | 2024 | Details |
Assumption-Lean (Causal) Modelling and Estimation: A Paradigm Shift from Traditional Statistical Modelling
Develop a flexible 'assumption-lean modelling' framework for causal inference that minimizes bias and enhances interpretability in statistical analyses using debiased learning techniques.
The missing mathematical story of Bayesian uncertainty quantification for big data
This project aims to enhance scalable Bayesian methods through theoretical insights, improving their accuracy and acceptance in real-world applications like medicine and cosmology.
Information Economics With Fundamental Uncertainty: Robustness, Commitment, and Strategic Incentives
This project explores how fundamental uncertainty affects learning and strategic information sharing, using decision-theoretic frameworks to enhance understanding of active experimentation and information dynamics.
Statistical theory and methodology for the combination of heterogeneous and distributed data
Develop new statistical methodologies to address data heterogeneity and measurement errors across diverse datasets, enhancing evidence-based advancements in science and policy.
Uniting Statistical Testing and Machine Learning for Safe Predictions
The project aims to enhance the interpretability and reliability of machine learning predictions by integrating statistical methods to establish robust error bounds and ensure safe deployment in real-world applications.