Limits of learning about a categorical latent variable under prior near-ignorance

DOI10.1016/J.IJAR.2008.08.003zbMATH Open1186.62007DBLPjournals/ijar/PiattiZTH09arXiv0904.4527OpenAlexW2133547295WikidataQ58012372 ScholiaQ58012372MaRDI QIDQ962884FDOQ962884

Authors: Alberto Piatti, M. Zaffalon, Fabio Trojani, Marcus Hutter 

Publication date: 7 April 2010

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

Abstract: In this paper, we consider the coherent theory of (epistemic) uncertainty of Walley, in which beliefs are represented through sets of probability distributions, and we focus on the problem of modeling prior ignorance about a categorical random variable. In this setting, it is a known result that a state of prior ignorance is not compatible with learning. To overcome this problem, another state of beliefs, called emph{near-ignorance}, has been proposed. Near-ignorance resembles ignorance very closely, by satisfying some principles that can arguably be regarded as necessary in a state of ignorance, and allows learning to take place. What this paper does, is to provide new and substantial evidence that also near-ignorance cannot be really regarded as a way out of the problem of starting statistical inference in conditions of very weak beliefs. The key to this result is focusing on a setting characterized by a variable of interest that is emph{latent}. We argue that such a setting is by far the most common case in practice, and we provide, for the case of categorical latent variables (and general emph{manifest} variables) a condition that, if satisfied, prevents learning to take place under prior near-ignorance. This condition is shown to be easily satisfied even in the most common statistical problems. We regard these results as a strong form of evidence against the possibility to adopt a condition of prior near-ignorance in real statistical problems.

Full work available at URL: https://arxiv.org/abs/0904.4527

Recommendations

• scientific article; zbMATH DE number 756709
• Publication:4864282
• Prior near ignorance for inferences in thek-parameter exponential family
• Imprecise probabilities for representing ignorance about a parameter
• A note on learning dependence under severe uncertainty

zbMATH Keywords

latent variablesimprecise Dirichlet modelnear-ignorance set of priors

Mathematics Subject Classification ID

Foundations and philosophical topics in statistics (62A01) Parametric inference (62F99) Statistical decision theory (62C99) Reasoning under uncertainty in the context of artificial intelligence (68T37)

Cites Work

• The Selection of Prior Distributions by Formal Rules
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Latent Variable Modeling of Diagnostic Accuracy
• An introduction to the imprecise Dirichlet model for multinomial data
• Theory and Applications of Models of Computation

Cited In (10)

• An aggregation framework based on coherent lower previsions: application to Zadeh's paradox and sensor networks
• Imprecise probability models for learning multinomial distributions from data. Applications to learning credal networks
• The Bayesian who knew too much
• Imprecise probabilities for representing ignorance about a parameter
• Belief function and multivalued mapping robustness in statistical estimation
• Comments on ``Imprecise probability models for learning multinomial distributions from data. applications to learning credal networks
• Rejoinder on ``Imprecise probability models for learning multinomial distributions from data. applications to learning credal networks
• A continuous updating rule for imprecise probabilities
• Credal ensembles of classifiers
• Learning imprecise probability models: conceptual and practical challenges

This page was built for publication: Limits of learning about a categorical latent variable under prior near-ignorance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q962884)