Bayes' Model of the Best-Choice Problem with Disorder
Author(s) -
Vladimir Mazalov,
Evgeny Ivashko
Publication year - 2011
Publication title -
international journal of stochastic analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.19
H-Index - 28
eISSN - 2090-3340
pISSN - 2090-3332
DOI - 10.1155/2012/697458
Subject(s) - mathematics , bayes' theorem , imperfect , random variable , decision maker , class (philosophy) , distribution (mathematics) , mathematical economics , statistics , artificial intelligence , computer science , bayesian probability , operations research , mathematical analysis , philosophy , linguistics
We consider the best-choice problem with disorderand imperfect observation. The decision-maker observes sequentiallya known number of i.i.d random variables from a known distributionwith the object of choosing the largest. At the random time the distributionlaw of observations is changed. The random variables cannotbe perfectly observed. Each time a random variable is sampled thedecision-maker is informed only whether it is greater than or less thansome level specified by him. The decision-maker can choose at mostone of the observation. The optimal rule is derived in the class ofBayes' strategies
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom