[Colloq] Title: Causal inference with partially revealed network interference | Panos Toulis, Harvard University | 3/1/16 10:30-11:30am 366WVH

[Walker, Lashauna]

Title: Causal inference with partially revealed network interference
Speaker: Panos Toulis, Harvard University
Date: 3/1/16  Time: 10:30-11:30am  Location: 366 WVH


Title: Causal inference with partially revealed network interference

Abstract:
 The interpretation of experiments is complicated when the outcome of an experimental unit depends not only on its assigned treatment but also on interferences from other units. Here, we extend the potential outcomes framework of causal inference without such interference between units (Rubin, 1974) in order to define and assess causal effects. When two units cannot interfere with each other, then one unit's treatment assignment only affects that unit's outcome. However, when two units can interfere with each other, then one unit's treatment assignment generally affects both of their outcomes. Furthermore, the interference can depend on units' characteristics and the treatment assignment itself, and is often only partially revealed. Our analysis of data generated by such situations uses both Bayesian and frequentist ideas to test sharp null hypotheses about causal effects. In particular, to assess causal effects we model and estimate the interference between units as a network, and develop novel testing procedures that involve repeated sampling of the treatment assignment under constraints from the network topology and the tested hypothesis. We illustrate our causal framework in applications where such forms of interference are ubiquitous but currently not adequately addressed.

Bio:
I obtained my B.Sc. in Electrical Engineering from the Aristotle University (Greece) in 2005, and worked on EU research projects in data mining between 2006-2008. In 2009, I moved to the U.S. and obtained my M.Sc. in Computer Science at Harvard, and in 2011 I joined the Statistics Ph.D. program. My main interests lie in the statistical modeling and causal understanding of complex socio-economic systems. Currently, I work on projects at the intersection of social networks, causal inference, and stochastic approximations. I received the 2015 Arthur P. Dempster prize at Harvard for my work in implicit stochastic gradient descent, and the 2013 Thomas R. Ten Have award for my work in causal inference with unit interference. In 2012, I worked with the Obama For America analytics team on experimental designs for voter mobilization through social media. My work has been generously supported by the 2009 Hellenic Harvard Foundation scholarship, the 2012 Google US/Canada Ph.D. Fellowship in Statistics, and the 2015 LinkedIn EGC award




Thank You.

LaShauna Walker
Events and Administrative Specialist
College of Computer and Information Science
Northeastern University
617-373-2763
Facebook<https://www.facebook.com/ccisatnu?ref=hl> | Instagram<https://instagram.com/ccisatnu/> | LinkedIn<https://www.linkedin.com/groups/Northeastern-University-College-Computer-Information-1943637?gid=1943637&mostPopular=&trk=tyah&trkInfo=idx%3A1-1-1%2CtarId%3A1426606862845%2Ctas%3ANortheastern+University+College+of+Com> | Twitter<https://twitter.com/CCISatNU>