A0156
Title: Nonparametric priors for partially exchangeable data: dependence structure and borrowing of information
Authors: Igor Pruenster - Bocconi University (Italy) [presenting]
Beatrice Franzolini - Bocconi University (Italy)
Antonio Lijoi - Bocconi University (Italy)
Giovanni Rebaudo - University of Turin and Collegio Carlo Alberto (Italy)
Abstract: Partial exchangeability is the ideal probabilistic framework for analyzing data from different, though related, sources. The implications of the induced dependence structure and borrowing of information across groups are explored. These findings inspire a new general class of nonparametric priors, termed multivariate species sampling models, which is characterized by its partially exchangeable partition probability function. This class encompasses several popular dependent nonparametric priors and has the merit of highlighting their core distributional properties.
