Recently the study of priors obtained as laws of suitably normalized random measures has gained some interest. As for all nonparametric priors the crucial point is the determination of the posterior distribution. In this paper a new and simple proof of the posterior characterization of a normalized random measure with independent increments is provided and an exact expression for the posterior distribution of their means is obtained. Finally an interesting particular case is treated in some detail.
Some issues in Bayesian Nonparamterics
PRUENSTER, Igor
2005-01-01
Abstract
Recently the study of priors obtained as laws of suitably normalized random measures has gained some interest. As for all nonparametric priors the crucial point is the determination of the posterior distribution. In this paper a new and simple proof of the posterior characterization of a normalized random measure with independent increments is provided and an exact expression for the posterior distribution of their means is obtained. Finally an interesting particular case is treated in some detail.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
