[Forum SIS] Seminar

[Simone Padoan]

Dear All,
We are glad to announce the following talk

*************************************************

DEC - Statistics Seminar - Università Bocconi,

Thursday, May 22nd, 2014, 

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

Time: 12:30pm

(The complete DEC seminars schedule is available at             
                 http://www.unibocconi.eu/statseminar)
*************************************************

Speaker 

Fabio Rigat
(Novartis Vaccines and Diagnostics Italia)

Title

"Model-based nonparametric estimation of absolute disease risk from case-control studies"

Abstract

 Case-control studies are ubiquitous tools for biomarker discovery, paving the way for prospective clinical trials assessing therapeutic and prophylactic clinical interventions targeting the discovered biomarkers. The primary endpoints of case-control studies traditionally use relative measures of disease risk, thereby estimating differences in biomarker distributions between the case and control groups. This approach does not attempt to contextualize the results of a case-control study within its epidemiological background. Absolute disease risk measures estimated from both case-control data and from disease incidence data provide this link, allowing for the quantification of the expected effects of biomarker-targeting interventions on the fraction of the population at risk having similar clinical profiles to those observed in the case-control study. This talk illustrates the theory and application of a statistical model leveraging on both parametric and nonparametric components of a mixture biomarker distribution to produce optimally smoothed absolute risk curves of Group B Streptococcus (GBS) infection in newborns. This mixture approach builds on well-known Bayesian nonparametric theory, by taking an empirical Bayes perspective. The optimally smoothed absolute disease risk curve shows that maternal antibody directed against the GBS capsule mediate protection of the newborn against early onset disease infection, thereby informing clinical development decision making. 



-- 
-----------------------------------------------

Dr. Simone Padoan, PhD.
Assistant Professor

Department of Decision Sciences
Bocconi University of Milan
via Roentgen, 1 20136 Milano - Italy
tel. +39 02 5836 5368
Email: simone.padoan a unibocconi.it
Webpage: http://faculty.unibocconi.it/simonepadoan
-----------------------------------------------

---
Dai il tuo 5x1000 alla Bocconi: aiuta a studiare chi merita, anche quando non puo'.
CF 80024610158.
www.unibocconi.it/5x1000

Please note that the above message is addressed only to individuals filing Italian income tax returns.
---