We consider the problem of Bayesian density deconvolution, when the mixing density is modelled as a Dirichlet-Laplace mixture. We give an assessment of the posterior accuracy in recovering the true mixing density, when it is itself a Laplace mixture. The results partially complement those in Donnet et al. (2014) and an application of them to empirical Bayes density deconvolution can be envisaged.
On Deconvolution of Dirichlet-Laplace Mixtures
Scricciolo, Catia
2016-01-01
Abstract
We consider the problem of Bayesian density deconvolution, when the mixing density is modelled as a Dirichlet-Laplace mixture. We give an assessment of the posterior accuracy in recovering the true mixing density, when it is itself a Laplace mixture. The results partially complement those in Donnet et al. (2014) and an application of them to empirical Bayes density deconvolution can be envisaged.
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.
