Motivated by a scheduling problem arising from serial sacrifice experiments, the asymptotic efficiency of irreversible adaptive allocation rules is studied. The asymptotic lower bound for the regret of an adaptive allocation rule is characterized by the minimum of a linear program. Based on a class of one-sided sequential tests, asymptotically efficient rules which achieve the lower bound are constructed. The conditions necessary for this construction are verified in the serial sacrifice scheduling problem.
Publié le : 1989-06-14
Classification:
Adaptive allocation rules,
sequential design,
sequential tests,
linear programming,
Kullback-Leibler information,
62L10,
62L05,
62P10
@article{1176347144,
author = {Hu, Inchi and Wei, C. Z.},
title = {Irreversible Adaptive Allocation Rules},
journal = {Ann. Statist.},
volume = {17},
number = {1},
year = {1989},
pages = { 801-823},
language = {en},
url = {http://dml.mathdoc.fr/item/1176347144}
}
Hu, Inchi; Wei, C. Z. Irreversible Adaptive Allocation Rules. Ann. Statist., Tome 17 (1989) no. 1, pp. 801-823. http://gdmltest.u-ga.fr/item/1176347144/