Premium
Sequential classification on partially ordered sets
Author(s) -
Tatsuoka Curtis,
Ferguson Thomas
Publication year - 2003
Publication title -
journal of the royal statistical society: series b (statistical methodology)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.523
H-Index - 137
eISSN - 1467-9868
pISSN - 1369-7412
DOI - 10.1111/1467-9868.00377
Subject(s) - mathematics , convergence (economics) , selection (genetic algorithm) , class (philosophy) , bayesian probability , finite set , set (abstract data type) , asymptotically optimal algorithm , state space , space (punctuation) , mathematical optimization , bayes' theorem , computer science , artificial intelligence , statistics , mathematical analysis , economics , programming language , economic growth , operating system
Summary. A general theorem on the asymptotically optimal sequential selection of experiments is presented and applied to a Bayesian classification problem when the parameter space is a finite partially ordered set. The main results include establishing conditions under which the posterior probability of the true state converges to 1 almost surely and determining optimal rates of convergence. Properties of a class of experiment selection rules are explored.