* Apologise for cross-posting *
Dear Colleagues,
I would like to inform you that a post-doc in Statistics is available in the Department of Statistics, Computer Science, Applications at the University of Florence, under the supervision of Prof. Monia Lupparelli and Prof. Francesco C. Stingo.
Deadline for application: July 12th 2021 Starting date: November 1st 2021
Research topic: Bayesian model search for profile undirected graphical models The research project aims to develop a graphical modelling approach to study the effect that a risk factor may have on a set of random variables and on their joint dependence structure. This issue could be partially addressed by using chain graph or multiple graph models: the first method ignores how the dependence structure may vary under different profiles defined by the external factor, the second does not account for the effect of the factor on single variables. The research should develop a class of profile graphical models to fill the gap between the existent graphical approaches. As far as inference is concerned, model selection represents a crucial aspect since compatibility constraints for the model identifiability need to be considered. The idea is to implement Bayesian stochastic search approaches for the selection and inference of discrete profile graphs, both for moderate and high dimensional data. The proposed methodology will be applied to biomedical data.
Details can be found at
https://bandi.miur.it/bandi.php/public/fellowship/id_fellow/192962 https://bandi.miur.it/bandi.php/public/fellowship/id_fellow/192962
and
https://titulus.unifi.it/albo/viewer?view=files%2F004108400-UNFICLE-701729a1... https://titulus.unifi.it/albo/viewer?view=files/004108400-UNFICLE-701729a1-86ee-4a07-8c93-2f0448df5b69-000.pdf
Best Regards, Monia Lupparelli
----------------------------------------- Monia Lupparelli, PhD Department of Statistics, Computer Science, Applications University of Florence Viale Morgagni 59, 50134 Florence, IT Phone +39 055 2751579