CMStatistics 2016: Start Registration
View Submission - CMStatistics
B0337
Title: Predictive density estimation: Recent results Authors:  Eric Marchand - Universite de Sherbrooke (Canada) [presenting]
Abstract: The estimation of predictive densities and their efficiency as measured by frequentist risk is addressed. For Kullback-Leibler, alpha-divergence, $L_1$ and $L_2$ losses, we review several recent findings that bring into play improvements by scale expansion, as well as duality relationships which lead to the study of plug-in estimators. A range of models are studied and include multivariate normal, scale mixtures of normals, Gamma, as well as models with restrictions on the parameter space.