[Forum SIS] avviso di seminario Prof. P. J. Green
Julia Mortera
mortera a uniroma3.it
Lun 3 Ott 2011 13:45:11 CEST
*
*************************AVVISO di SEMINARIO del Prof. Peter
GREEN***********************
*
Nell'ambito del dottorato in Metodi Statistici per l'Economia e
l'Impresa della Scuola dottorale in Economia e Metodi
Quantitativi
presso il Dipartimento di Economia, Università degli Studi Roma Tre, Via
Silvio D'Amico 77, 00145 Roma
*mercoledì 19 ottobre 2011 alle ore 16:30, aula 24 - 3° piano *
*Prof. Peter Green
Department of Mathematics
University of Bristol, UK
*
terrà il seminario
*Bayesian graphical model determination *
*Abstract*
The structure in a multivariate distribution is largely captured by the
conditional independence relationships that hold among the variables,
often represented graphically, and inferring these from data is an
important step in understanding a complex stochastic system.
Simultaneous inference about the conditional independence graph and
parameters of the model is known as joint structural and quantitative
learning in the machine learning literature: it is appealing to conduct
this in Bayesian paradigm, but this can pose computational challenges,
because of the huge size of the model space that is involved, unless
there are very few variables. After setting the scene, I will present
some recent joint work with Alun Thomas (Utah), that exploits new
results on perturbations to graphs that maintain decomposability and on
enumeration of junction trees to construct a Markov chain sampler on
junction trees that can be used to compute joint inference about
structure and parameters in graphical
models on quite a large scale.
~ ~ ~
*mercoledì 26 ottobre 2011 ore 16:30 aula 24 - 3° piano *
*Prof. Peter Green
*
terrà il seminario
*
*
*Identifying influential model choices in Bayesian hierarchical models *
*Abstract*
Real-world phenomena are frequently modelled by Bayesian hierarchical
models. The building blocks in such models are the distributions of each
variable conditional on parent and/or neighbour variables in the graph.
The specifications of centre and spread of these conditional
distributions may be well-motivated, while the tail specifications are
often left to convenience. However, the posterior distribution of a
parameter may depend strongly on such arbitrary tail specifications.
This is not easily detected in complex models.
In this paper we propose a graphical diagnostic which identifies such
influential statistical modelling choices at the node level in any chain
graph model. Our diagnostic, the local critique plot, examines local
conflict between the information coming from the parents and neighbours
(local prior) and from the children and co-parents (lifted likelihood).
It identifies properties of the local prior and the lifted likelihood
that are influential on the posterior density. We illustrate the use of
the local critique plot with applications involving models of different
levels of complexity. The local critique plot can be derived for all
parameters in a chain graph model, and is easy to
implement using the output of posterior sampling
~ ~ ~
*Tutti gli interessati sono invitati a partecipare*
--
Julia Mortera
Dipartimento di Economia
Università Roma Tre
Via Silvio D'Amico 77
00145 Roma
Tel: +39 06 57335732
Fax: +39 06 57335771
URL: http:http://dipeco.uniroma3.it/docenti.asp?id=123&nomedocente=Julia%20Mortera
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20111003/36709b33/attachment-0001.html>
Maggiori informazioni sulla lista
Sis