Computable priors sharpened into Occam's razors

FieldValue
dc.contributor.authorBickel, David R.
dc.date.accessioned2017-01-03T22:14:03Z
dc.date.available2017-01-03T22:14:03Z
dc.date.issued2016-12-30
dc.identifier.urihttp://davidbickel.com
dc.identifier.urihttp://hdl.handle.net/10393/35661
dc.description.abstractThe posterior probabilities available under standard Bayesian statistics are computable, apply to small samples, and coherently incorporate previous information. Modifying their priors according to results from algorithmic information theory adds the advantage of implementing Occam's razor, giving simpler distributions of data higher prior probabilities.
dc.language.isoen
dc.subjectBayesian inference
dc.subjectprior probability
dc.titleComputable priors sharpened into Occam's razors
dc.typeWorking Paper
CollectionMathématiques et statistiques // Mathematics and Statistics

Files
algorithm161230.pdf115.45 kBAdobe PDFOpen