Sanov's theorem on the asymptotic behavior of probabilities of large deviations for an empirical probability distribution is established under different conditions than previously given by Sanov, Hoadley and Stone. The new conditions are based on likelihood ratio approximations rather than on multinomial approximations. It is shown that these conditions are strictly more general than those of Stone.
Publié le : 1976-07-14
Classification:
Large deviations,
exact slope,
empirical probability measures,
likelihood ratio,
60F10,
62F20,
62G20
@article{1176343548,
author = {Sievers, Gerald L.},
title = {Probabilities of Large Deviations for Empirical Measures},
journal = {Ann. Statist.},
volume = {4},
number = {1},
year = {1976},
pages = { 766-770},
language = {en},
url = {http://dml.mathdoc.fr/item/1176343548}
}
Sievers, Gerald L. Probabilities of Large Deviations for Empirical Measures. Ann. Statist., Tome 4 (1976) no. 1, pp. 766-770. http://gdmltest.u-ga.fr/item/1176343548/