[Forum SIS] DEC Bocconi - Statistics Seminars - May 4th 2017, D. Durante

[Raffaella Piccarreta]

Dear all, 

we are glad to announce the next: 



DEC - Statistics Seminar 

Thursday, May 4 th , 2017 

Bocconi University 

12:30 pm 

Room 3-E4-SR03, Via Rontgen 1 - 3rd floor 





Daniele Durante ( Università degli Studi di Padova) 



Models and Computational Methods for Bayesian Density Regression 



Abstract 

There is considerable interest in studying how the distribution of an outcome varies with a set of predictors. Bayesian nonparametric dependent mixture models provide a useful direction to flexibly address this goal, however many representations are characterized by intractable computational methods and difficult interpretation. To address these issues, I will discuss a flexible class of predictor-dependent Gaussian mixture models, which relies on a constructive characterization of the stick-breaking representation via a set of continuation-ratio logistic regressions, facilitating analytical derivation of routine-use algorithms in Bayesian inference. These models have appealing theoretical properties in asymptotic contexts, but their considerable flexibility comes at a cost in terms of efficiency and parsimony. Motivated by quantitative risk assessment studies in toxicology applications, I will additionally introduce a class of convex mixture regression models that allow the entire distribution of an health outcome to be unknown and changing with the dose of a potentially adverse exposure. In particular the model relies on a flexible characterization of the density at the extreme dose levels, and expresses the conditional density at each intermediate dose as a convex combination of the extremal densities. This formulation massively reduces dimensionality compared to unstructured predictor-dependent Gaussian mixture models, without substantially affecting flexibility in a wide range of toxicology studies. 



Kind regards, 

Raffaella Piccarreta and Isadora Antoniano 



The DEC statistics seminars schedule is available at http://www.unibocconi.eu/statseminar 



ATTENTION: 

If you are a guest and you do not have a Bocconi ID Card to access to the Bocconi Buildings, please confirm your participation by sending an email to simona.gagino a unibocconi.it 
In addition, we suggest to print, fill out and send the attached form (to give your consent to personal data handling) via email to the same address. In this way, the check-in procedure at the entrance will be faster and easier. 
-- 
*************************************************** 
Raffaella Piccarreta 
Associate Professor - Statistics 
DEC - Department of Decision Sciences, 
Universita' L.Bocconi, via Guglielmo Röntgen 1 (3rd floor, room D1-09). 20136, Milano. 
email: piccarreta a unibocconi.it 
tel. +39-02-58365659 / fax +39-02-58365630 

Web page (ENGLISH VERSION): http://faculty.unibocconi.eu/raffaellapiccarreta/ 
(ITALIAN VERSION): http://faculty.unibocconi.it/raffaellapiccarreta/ 
*************************************************** 
---
Dai il tuo 5x1000 alla Bocconi.
Aiuta gli studenti meritevoli a costruire il proprio futuro.
CF 80024610158.
www.unibocconi.it/5x1000

Please note that the above message is addressed only to individuals filing Italian income tax returns.
5x1000 is a percentage of Italian personal income tax that taxpayers can allocate to Universities, scientific research and non profit organizations.
---
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20170428/5960b08d/attachment-0001.html>
-------------- parte successiva --------------
Un allegato non testuale è stato rimosso....
Nome:        ModuloVisitorPass&Privacy.pdf
Tipo:        application/pdf
Dimensione:  56070 bytes
Descrizione: non disponibile
URL:         <http://www.stat.unipg.it/pipermail/sis/attachments/20170428/5960b08d/attachment-0001.pdf>