Learning about a Categorical Latent Variable under Prior Near-Ignorance

dc.creatorPiatti, Alberto
dc.creatorZaffalon, Marco
dc.creatorTrojani, Fabio
dc.creatorHutter, Marcus
dc.date2007-05-29
dc.date.accessioned2026-07-07T09:46:28Z
dc.date.available2026-07-07T09:46:28Z
dc.descriptionIt is well known that complete prior ignorance is not compatible with learning, at least in a coherent theory of (epistemic) uncertainty. What is less widely known, is that there is a state similar to full ignorance, that Walley calls near-ignorance, that permits learning to take place. In this paper we 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 latent. We argue that such a setting is by far the most common case in practice, and we show, for the case of categorical latent variables (and general manifest variables) that there is a sufficient condition that, if satisfied, prevents learning to take place under prior near-ignorance. This condition is shown to be easily satisfied in the most common statistical problems.
dc.description15 LaTeX pages
dc.identifierhttps://arxiv.org/abs/0705.4312
dc.identifierhttp://arxiv.org/abs/0705.4312
dc.identifierProc. 5th International Symposium on Imprecise Probability: Theories and Applications (ISIPTA 2007) pages 357-364
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/163542
dc.subjectProbability
dc.subjectStatistics Theory
dc.titleLearning about a Categorical Latent Variable under Prior Near-Ignorance
dc.typetext

Files

Collections