[Statlist] Swiss Statistics Seminar - Oct. 25, 2019 - Titles + Abstracts

[b@rheii m@iii@g oii @im@uzh@ch]

Dear all,

We would like to invite you to and remind you of the next Swiss Statistics Seminar:

Date, Time, Place
----------------
Friday, October 25, 2019
14:15 - 17:45
University of Bern
Institut für Exakte Wissenschaften
Lecture Hall B7 (talks) & Foyer (coffee/tea, poster session)

... with the following invited speakers and their topics (abstracts below):

* Jonas Peters - University of Copenhagen, Denmark
>> Towards using causality in the sciences<<

* Patrick Wolfe - Purdue University, USA 
>> Modeling Large Networks and Network Populations <<

Schedule
-------
14:15-14:45 Welcome coffee/tea
14:45-15:45 Talk by Jonas Peters
15:45-16:45 Break with apéro and poster session
16:45-17:45 Talk by Patrick Wolfe

Poster Session
------------
We warmly encourage everyone, and in particular PhD students and postdocs,
to take advantage of the poster session to present their work.

Registration
-----------
Registration for attendance is not required.

Website
-------
www.imsv.unibe.ch/research/talks/swiss_statistics_seminars_live/index_eng.html

We are looking forward to seeing many of you in Bern!

Kind regards,

Lutz Dümbgen (Uni Bern), Barbara Hellriegel (SSS) and Marloes Maathuis (ETH)
for the organizing committee

========== Abstracts ===================

Jonas Peters - University of Copenhagen, Denmark
------------
>> Towards using causality in the sciences <<

In many real world problems, we are interested in knowing how a system
responds to interventions. Such interventional effects can be predicted
whenever a causal model (rather than a classical statistical model) of
the underlying data generating process is available. But even if the
research question at hand is not an interventional question, causal
ideas may prove to be helpful. When generalizing predictive models to
unseen experimental conditions, for example, causal concepts may
indicate which part of the model can be assumed to be invariant.
Applying causal methods and ideas in the sciences, however, comes with
several difficulties: causal knowledge is usually sparse, assumptions
are hard to test and the data have complex dependencies. In this talk,
we present two simple applications of causal concepts in the sciences:
computing causal effects in spatio-temporal data from biogeography and
generalizing models of metabolic networks to unseen experiments. No
prior knowledge on causality is required.

Website: http://web.math.ku.dk/~peters


Patrick J. Wolfe - Purdue University, USA
----------------
Frederick L. Hovde Dean of Science and Miller Family Professor of 
Statistics and Computer Science, 

>> Modeling Large Networks and Network Populations <<

How do we draw sound and defensible conclusions from big data, for example 
in comparing two sets of observations, or evaluating goodness of model fit? 
In this talk I will discuss the current state of the art in one area of 
particular interest: big network data.  Progress in this area includes the 
development of new large-sample theory that helps us to view and interpret 
networks as statistical data objects, along with the transformation of this 
theory into new statistical methods to model and draw inferences from 
network data in the real world. The insights that result from connecting 
theory to practice also feed back into pure mathematics and theoretical 
computer science, prompting new questions at the interface of combinatorics, 
analysis, probability, and algorithms.

Biosketch and photo: https://signalprocessingsociety.org/professional-development/distinguished-lecturers#dexp-accordion-item--6