Seminar: Circular Statistics with R

Lecturer: Prof. Arthur Pewsey, Escuela Politécnica, Universidad de Extremadura, Spain

Place and time: Monday Dec 2nd at 11 a.m. (first class) Room B, Santa Marta.

Seminar: An Introduction to Time Series Analysis with R

Lecturer: Prof. Lucia Aguilar Zuil, Escuela Politécnica, Universidad de Extremadura, Spain

Place and time: Monday Dec 2nd at 11 a.m. (first class) Room F, Dept of Ecomonics, San Giobbe.

Happy Birthday GNU!

The GNU system is thirty years old today!


I would like to share with you the below email I got today. Claudio

30 years ago, Richard Stallman published the announcement that would launch the free software movement.

Celebrate software freedom online and at events being held all around the world. Visit our [Web page][1] to register for the big shebang in Boston, take action online, and learn about satellite events being held around the world.

  1. Celebrate online with GNU-a-Days and more

Looking for an easy way to get in on the fun and support software freedom? Check out our [GNU-a-Days][1], daily challenges you can take throughout the month of September. Show your GNU pride by grabbing our special 30th anniversary Web badge for your site or profile picture. You can also make a [special 30th anniversary donation][2] to ensure that the GNU system enters its next decade stronger than ever. It's all at [our special GNU 30th Web page][1].

  1. 30th anniversary celebration and hackathon in Cambridge

Have you [registered][3] for the big anniversary bash on September 27 - 29 in Cambridge, MA yet?

GNU system founder Richard Stallman will be there, as will many of GNU's early participants and the maintainers of GNU projects.

In addition to cake and special remarks from Richard Stallman, the anniversary celebration will take the form of a hackathon. The hackathon will focus on important needs for free software in today's Internet-based world. Hackathon participants will include many GNU projects and other free software projects that fit the theme. They

include: coreboot, Gnash, GNOME, GNU FM, GNU MediaGoblin?, GNU social,

Tahoe-LAFS, Tor, and others.

  1. Satellite events

GNU supporters all over the world are planning their own celebrations, and we've listed them all on the [30th anniversary page][1]. Events are currently in the works in Buenos Aires, Argentina; Cox's Bazaar, Bangladesh; Kitchener, Canada; Prague, Czech Republic; Paris, France; and Tokyo, Japan. Check back often for new additions. To host a satellite event in your area, contact <>.

No matter who you are or where you live, we hope you'll find a way to celebrate the [30th anniversary of the GNU system][1].

Happy Hacking,

Libby Reinish FSF Campaigns Manager on behalf of GNU

[1]: "GNU's 30th anniversary" [2]: "Support the FSF" [3]: "GNU 30th anniversary celebration and hackathon"

Valutazione e università, i sociologi tedeschi boicottano i ranking accademici

Una collega del Dipartimento di Studi Linguistici e Culturali Comparati, Francesca Coin ha scritto sul suo blog un post interessante, puoi leggerlo qui.

Usa: laureati pagati solo 10 dollari l’ora? Class action contro le università

Negli Stati Uniti gli avvocati Strauss e Anziska portano avanti la denuncia collettiva degli studenti di una ventina di facoltà, ritenute colpevoli di avere “violato le leggi a tutela dei consumatori diffondendo dati falsi circa le percentuali di laureati che trovano lavoro dopo i loro diplomi”

Leggi l'articolo intero qui.

Close Windows, Open Doors

Announce of Seminar

Prof. Ruben Zamar

Department of Statistics University of British Columbia

Ensembling Classification Models Based on Phalanxes of Variables with Applications in Drug Discovery

21 March 2013 at 10.30am

Aula ex Consiglio di Statistica Palazzo Ala C2 San Giobbe, Venezia

Anyone interested is invited to participate


Statistical detection of rare cases in highly unbalanced two class situations is an interesting and challenging problem. We are interested in detecting rare chemical compounds that are active against a biological target, such as lung cancer tumor cells, as part of a drug discovery process. Instead of predicting the classes of the compounds, we rank all of the compounds in terms of their probability of activity to produce a shortlist containing the maximum number of actives. We have used four assay datasets and five rich - in terms of number of variables – descriptor sets for each of the four assays. Capitalizing on the richness of variables in a descriptor set, we form the phalanxes by grouping variables together. The variables in a phalanx are good to put together, whereas the variables in different phalanxes are good to ensemble. We then form our ensemble by growing a random forest in each phalanx and aggregating them over the phalanxes. The performance of the ensemble of phalanxes is found to be better than its competitors random forest and regularized random forest. Our ensemble performs very well when there are many variables in a descriptor set and when the proportion of active compounds is very small. In other words, the harder the problem is the better the ensemble of phalanxes performs relative to alternative procedures.

Call for a Research Fellowship Position at DAIS


Nuovi sviluppi per l’analisi di serie temporali di dati ecologici e ambientali Advances in time series analysis for ecological and environmental data

  • 05/C Ecology Scientific Disciplinary Sector BIO/7 Ecology
  • 03/A Analytical, Chemical and physical - Scientific Disciplinary Sector CHIM/12 Chemistry of the environment and cultural heritage
  • 13/D Statistical and mathematical methods for decisions Scientific Disciplinary Sector SECS-S/01 statistics
Duration: 12 months
Deadline: 10/04/2013 (This is a re-open call)

Full documentation (Italian and English) is available here and here

Workshop on


8-9 October 2012

Ca’ Foscari - Aula Baratto Dorsoduro 3246 – Venezia

Final meeting of the PRIN 2008 research projects:

Likelihood and nonparametric statistical techniques with some applications

Local partners: University of Roma "La Sapienza", University of Cagliari

Approximate Likelihood Methods for High-Dimensional Dependencies

Local partners: University of Udine, University of Padua, Ca' Foscari University of Venice, University of Verona

For further information:

Download the Poster