Mixtures of Dirichlet Processes with Applications to Bayesian Nonparametric Problems

摘要: process. This paper extends Ferguson's result to cases where the random measure is a mixing distribution for parameter which determines from observations are made. The conditional of measure, given observations, no longer that simple Dirichlet process, but can be described as being mixture processes. gives formal definition these mixtures and develops several theorems about their properties, most important closure property such mixtures. Formulas computing derived applications problems in bio-assay, discrimination, regression, distributions given.