Bayesian posteriors for arbitrarily rare events

DOI10.1073/PNAS.1618780114MaRDI QIDQ4646121zbMATH OpenOpenAlexWikidataFDO

Authors Drew Fudenberg, Kevin X. He, Lorens A. Imhof

Publication date 11 January 2019

Published in Proceedings of the National Academy of Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1608.05002

Mathematics Subject Classification ID

Bayesian inference (62F15) Statistics of extreme values; tail inference (62G32)

Abstract: We study how much data a Bayesian observer needs to correctly infer the relative likelihoods of two events when both events are arbitrarily rare. Each period, either a blue die or a red die is tossed. The two dice land on side $1$ with unknown probabilities $p_1$ and $q_1$, which can be arbitrarily low. Given a data-generating process where $p_{1}gec{q}_1$, we are interested in how much data is required to guarantee that with high probability the observer's Bayesian posterior mean for $p_1$ exceeds $(1-delta)c$ times that for $q_1$. If the prior densities for the two dice are positive on the interior of the parameter space and behave like power functions at the boundary, then for every $epsilon>0,$ there exists a finite $N$ so that the observer obtains such an inference after $n$ periods with probability at least $1-epsilon$ whenever $n{p}_{1}geN$. The condition on $n$ and $p_1$ is the best possible. The result can fail if one of the prior densities converges to zero exponentially fast at the boundary.

Recommendations

• Expert information and nonparametric Bayesian inference of rare events
• Conditioning out rare events for exponential families has negligible effect on inference
• BETTER PRIORS FOR BAYESIAN BETTORS
• Bayesian inference does not lead you astray\dots on average
• Bayesian analysis of rare events

Cited in

(6)

• Rare-event detection by Quasi-Wang-Landau Monte Carlo sampling with approximate Bayesian computation
• Expert information and nonparametric Bayesian inference of rare events
• Player-compatible learning and player-compatible equilibrium
• Pathwise concentration bounds for Bayesian beliefs
• Spatial distribution of the earthquake in mainland China
• Observability, dominance, and induction in learning models

This page was built for publication: Bayesian posteriors for arbitrarily rare events

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4646121)