Safe probability

DOI10.1016/J.JSPI.2017.09.014zbMATH Open1383.62014arXiv1604.01785OpenAlexW4212862216MaRDI QIDQ1698993FDOQ1698993

Authors: Peter D. Grünwald 

Publication date: 16 February 2018

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Abstract: We formalize the idea of probability distributions that lead to reliable predictions about some, but not all aspects of a domain. The resulting notion of `safety' provides a fresh perspective on foundational issues in statistics, providing a middle ground between imprecise probability and multiple-prior models on the one hand and strictly Bayesian approaches on the other. It also allows us to formalize fiducial distributions in terms of the set of random variables that they can safely predict, thus taking some of the sting out of the fiducial idea. By restricting probabilistic inference to safe uses, one also automatically avoids paradoxes such as the Monty Hall problem. Safety comes in a variety of degrees, such as "validity" (the strongest notion), "calibration", "confidence safety" and "unbiasedness" (almost the weakest notion).

Full work available at URL: https://arxiv.org/abs/1604.01785

Recommendations

• Safe probability: restricted conditioning and extended marginalization
• Verification, Model Checking, and Abstract Interpretation
• Safe and Effective Importance Sampling
• On safe tractable approximations of chance constraints
• Satisfying safety goals by probabilistic risk assessment.
• Probabilistic model-based safety analysis
• Bounding the risk probability
• Playing Safe

zbMATH Keywords

unbiasednesscalibrationprobability distributionsvaliditysafetyMonty Hall problemconfidence safety

Mathematics Subject Classification ID

Bayesian inference (62F15) Foundations and philosophical topics in statistics (62A01)

Cites Work

• The Well-Calibrated Bayesian
• Confidence distribution, the frequentist distribution estimator of a parameter: a review
• Title not available (Why is that?)
• Almost the best of three worlds: risk, consistency and optional stopping for the switch criterion in nested model selection
• Title not available (Why is that?)
• Confidence and Likelihood^*
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Causality. Models, reasoning, and inference
• 10.1162/jmlr.2003.3.4-5.993
• Title not available (Why is that?)
• Title not available (Why is that?)
• Maxmin expected utility with non-unique prior
• Fiducial theory and optimal inference
• Some Problems Connected with Statistical Inference
• Probability with Martingales
• Title not available (Why is that?)
• Inferential Models: A Framework for Prior-Free Posterior Probabilistic Inference
• Introduction to imprecise probabilities
• The functional-model basis of fiducial inference
• Title not available (Why is that?)
• Title not available (Why is that?)
• Robust probability updating
• Making decisions using sets of probabilities: updating, time consistency, and calibration
• Asymptotic calibration
• Title not available (Why is that?)
• Philosophy of statistics.
• Dilation for sets of probabilities
• R. A. Fisher's fiducial argument and Bayes' theorem
• Conditional Probability
• R. A. Fisher in the 21st century. Invited paper presented at the 1996 R. A. Fisher lecture. (With comments).
• Title not available (Why is that?)
• Title not available (Why is that?)
• The Proper Fiducial Argument
• Confidence, Likelihood, Probability
• Fiducial and confidence distributions for real exponential families
• Coverage probability bias, objective Bayes and the likelihood principle
• Safe probability: restricted conditioning and extended marginalization

Cited In (9)

• Playing Safe
• Minimum description length revisited
• A comparison of learning rate selection methods in generalized Bayesian inference
• False confidence, non-additive beliefs, and valid statistical inference
• Confidence distributions and related themes
• Safe probability: restricted conditioning and extended marginalization
• Verification, Model Checking, and Abstract Interpretation
• Model misspecification, Bayesian versus credibility estimation, and Gibbs posteriors
• Valid inferential models for prediction in supervised learning problems

This page was built for publication: Safe probability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1698993)