Invited Session Bayesian contributions to Statistical Learning Organizer/Chair: Federico Camerlenghi (Università di Milano-Bicocca) Discussant: Alessandra Guglielmi (Politecnico di Milano) Room: T32 Floor: ground Short summary: Bayesian statistical methods include a large variety of effective tools to face prediction, statistical learning and estimation via a principled approach.
The session is focused on some recent hierarchical Bayesian models, which are designed for different applied problems arising, e.g., in precision medicine and cancer detection.
Both Bayesian parametric and nonparametric methods will be discussed.
#
Papers
1.
A Bayesian framework for early cancer screening Author(s) Jeff Miller Sally Paganin
2.
Imputing Synthetic Pseudo Data from Aggregate Data: Development and Validation for Precision Medicine Author(s) Cecilia Balocchi
3.
Linear models with assumptions-free residuals: a Bayesian Nonparametric approach. Author(s) Filippo Ascolani Valentina Ghidini
Dipartimento di Scienze Economiche e Sociali (Di.S.E.S.)