[Forum SIS] [seminario] "Quantum Tea Party Seminars", Università di Milano.

[stefano iacus]

Ho il piacere di annunciare un pomeriggio seminariale improvvisato, dunque straordinario, dal titolo:

"Quantum Tea Party Seminars" 

che avrà luogo presso il 
Dipartimento di Scienze Economiche, Aziendali e Statistiche
Via Conservatorio 7, Milano

Il giorno 17 febbrario 2012, alle ore 14:30 presso l'Aula 26

Gli interventi saranno a cura di Richard Gill e Yoichi Nishiyama. Di seguito titolo e abstract di ciascun seminario.

Richard Gill
Mathematical Institute
Leiden University, Netherlands

Titolo: "Quantum statistics in the real world?"

Abstract: 
It has been claimed that random phenomena connected to quantum physics disobey the usual rules of classical probability theory, and that a more general probability theory is required to describe these phenomena. One of the main features of this theory is so-called non-commutativity, and one of the consequences of non-commutativity is that when we try to measure a quantum system, we disturb it. Now statisticians working on problems from social and behavioural science, economics, or psychology and neuroscience are well aware that when we try to observe such systems we inevitably disturb them. And our business, as statisticians, is concerned with making statements about causality by analysing complex observational data in precisely such situations. Could quantum probability be useful to us, in these fields too?

I will briefly survey the mathematical description of quantum states and measurements, discuss quantum non-locality (from Einstein-Podolsky-Rosen to the Bell inequalities and beyond) and the Schrödinger cat problem (measurement problem), and finish with a glimpse at some recent developments in quantum statistics. My conclusion is that there is lots for real statisticians to contribute at the moment in the quantum physics lab. I will explain why, on the other hand, I am rather sceptical about the usefulness of quantum probability outside of the quantum world.


Yoichi Nishiyama
Institute of Mathematical Statistics
Tokyo, Japan

Titolo: Some results for change point problems

Abstract:
In the first part of the talk which is based on a joint work with Ilia Negri, I explain an idea to construct test statistics for the parametric change point problem by the simple case of independent sequence, and then the idea  is extended to stochastic process cases.  Applications to diffusion process models are mentioned. 
In the second part of the talk, the most typical non-parametric change point problem for independent sequence is considered, and I present a new test statistic based on the rank statistics.



Sono ammessi gatti di Schrödinger purché in scatola. Non verrà servito il tè.



-----------------------------------
Stefano M. Iacus
Department of Economics,
Business and Statistics
University of Milan
Via Conservatorio, 7
I-20123 Milan - Italy
Ph.: +39 02 50321 461
Fax: +39 02 50321 505
http://www.economia.unimi.it/iacus
------------------------------------------------------------------------------------
Please don't send me Word or PowerPoint attachments if not 
absolutely necessary. See:
http://www.gnu.org/philosophy/no-word-attachments.html