BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Talks.cam//talks.cam.ac.uk// X-WR-CALNAME:Talks.cam BEGIN:VEVENT SUMMARY:Bayesian modelling of Dupuytren disease using Gaussian copula grap hical models - Reza Mohammadi (Universiteit van Tilburg\; University of Gr oningen) DTSTART:20160826T084000Z DTEND:20160826T092000Z UID:TALK67067@talks.cam.ac.uk CONTACT:INI IT DESCRIPTION:Co-authors: Fentaw Abegaz (University of Liege\, Belgiu m)\, Edwin van den Heuvel (Eindhoven University of Technology\, The Nethe rlands)\, Ernst Wit (University of Groningen\, The Netherlands)

Dupuytren disease is a fibroproliferative disorder with unkno wn etiology that often progresses and eventually can cause permanent cont ractures of the affected fingers. In this talk\, we provide a computation ally efficient Bayesian framework to discover potential risk factors and investigate which fingers are jointly affected. Our Bayesian approach is based on Gaussian copula graphical models\, which provide a way to discov er the underlying conditional independence structure of variables in mult ivariate mixed data. In particular\, we combine the semiparametric Gaussi an copula with extended rank likelihood to analyse multivariate mixed dat a with arbitrary marginal distributions. For the structural learning\, we construct a computationally efficient search algorithm using a trans-dim ensional MCMC algorithm based on a birth-death process. In addition\, to make our statistical method easily accessible to other researchers\, we h ave implemented our method in C++ and provide an interface with R software as an R package BDgraph\, which is freely available online. \; LOCATION:Seminar Room 1\, Newton Institute END:VEVENT END:VCALENDAR