[Forum SIS] DEC - Statistics Seminar - November 17th

[Isadora Antoniano]

We are glad to announce the next:

*DEC - Statistics Seminar*


*Thursday, November 17th*

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

Time: *12:30 pm*




*Omiros Papaspiliopoulos *(Universitat Pompeu Fabra Barcelona)



*Scalable Bayesian variable selection and model averaging under block
orthogonal design*

*Abstract:*
We show how to carry out fully Bayesian variable selection and model
averaging in linear models when both the number of observations and
covariates are large. We work under the assumption that the Gram matrix is
block-diagonal, and carry out fully Bayesian inference where the residual
variance is integrated out when computing posterior model probabilities.
Our approach returns the most probable model of any given size without
resorting to any integration, posterior probabilities for any number of
models by evaluating a single one-dimensional integral, and other
quantities of interest such as variable inclusion probabilities and model
averaged regression estimates by carrying out an adaptive, deterministic
one-dimensional numerical integration.  Our approach, albeit fully
Bayesian, does not require Markov Chain Monte Carlo sampling. The overall
computational cost scales linearly with the number of blocks, which can be
processed in parallel, and exponentially with the block size, rendering it
most adequate in situations where predictors are organized in many
moderately-sized blocks. When the design is not block-diagonal we show how
our approach combined with block-diagonal approximations, such as spectral
clustering, to identify high-probability models. In the talk we will also
link this approach with interesting current developments in
high-dimensional variable selection, such DECO and related screening
methods.

(joint work with David Rossell, UPF)

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


Kind regards,
*Raffaella Piccarreta and Isadora Antoniano*



*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.


***************************************************
Isadora Antoniano Villalobos

Assistant Professor
DEC - Department of Decision Sciences,
Bocconi University, via Guglielmo Röntgen 1 (3rd floor, room D1-16). 20136,
Milano.
email: isadora.antoniano a unibocconi.it

Web page: http://faculty.unibocconi.eu/isadoraantonianovillalobos
***************************************************
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20161114/7a33dffe/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/20161114/7a33dffe/attachment-0002.pdf>
-------------- parte successiva --------------
Un allegato non testuale è stato rimosso....
Nome:        O.Papaspiliopoulos. 17.11.16 .pdf
Tipo:        application/pdf
Dimensione:  25432 bytes
Descrizione: non disponibile
URL:         <http://www.stat.unipg.it/pipermail/sis/attachments/20161114/7a33dffe/attachment-0003.pdf>