This paper introduces and studies a new class of nonparametric prior distributions. Random probability distribution functions are constructed via normalization of random measures driven by increasing additive processes. In particular, we present results for the distribution of means under both prior and posterior conditions and, via the use of strategic latent variables, undertake a full Bayesian analysis. Our class of priors includes the well-known and widely used mixture of a Dirichlet process.
Publié le : 2004-12-14
Classification:
Bayesian nonparametric inference,
distribution of means of random probability measures,
increasing additive process,
Lévy measure,
mixtures of Dirichlet process,
62F15,
60G57
@article{1107794871,
author = {Nieto-Barajas, Luis E. and Pr\"unster, Igor and Walker, Stephen G.},
title = {Normalized random measures driven by increasing additive processes},
journal = {Ann. Statist.},
volume = {32},
number = {1},
year = {2004},
pages = { 2343-2360},
language = {en},
url = {http://dml.mathdoc.fr/item/1107794871}
}
Nieto-Barajas, Luis E.; Prünster, Igor; Walker, Stephen G. Normalized random measures driven by increasing additive processes. Ann. Statist., Tome 32 (2004) no. 1, pp. 2343-2360. http://gdmltest.u-ga.fr/item/1107794871/