Confidence intervals, significance values, maximum likelihood estimates, etc. sharpened into Occam's razors

Autor:	David R. Bickel
Přispěvatelé:	University of Ottawa [Ottawa], University of Ottawa ( University of Ottawa ), University, Bickel, David R.
Jazyk:	angličtina
Rok vydání:	2018
Předmět:	Statistics and Probability fiducial inference [ STAT.OT ] Statistics [stat]/Other Statistics [stat.ML] 0211 other engineering and technologies Kolmogorov complexity 02 engineering and technology occam [STAT.OT]Statistics [stat]/Other Statistics [stat.ML] 01 natural sciences differential entropy Differential entropy 010104 statistics & probability [ INFO.INFO-IT ] Computer Science [cs]/Information Theory [cs.IT] Statistics Statistics::Methodology 0101 mathematics probability matching prior distribution computer.programming_language Mathematics 021103 operations research confidence distribution algorithmic probability [STAT.OT] Statistics [stat]/Other Statistics [stat.ML] Confidence interval Statistics::Computation Sampling distribution [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT] Fiducial inference Confidence distribution Algorithmic probability [INFO.INFO-IT] Computer Science [cs]/Information Theory [cs.IT] computer
Popis:	Confidence sets, p values, and maximum likelihood estimates may be adjusted to favor sampling distributions that are simple compared to others in the parametric family. The adjustments are derived from a prior likelihood function previously used to adjust posterior distributions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f94c6934c6023a090052d34c0c2d9f31 https://hal.archives-ouvertes.fr/hal-01799519v2/file/approximation-preprint-v2.pdf Zobrazit plný text záznamu