Date: Friday, November 16, 2012

Speaker: Edoardo Airoldi, Assistant Professor of Statistics, Harvard University 

Location: Maxwell-Dworkin G125, 33 Oxford Street, Cambridge, MA 02138

Time: Informal lunch with speaker, 12:30pm. Talk, 1:00pm.

Title: Design and Analysis of Experiments that Leverage Social Structure and Interactions

Abstract: A number of scientific endeavors of current national and international interest involve populations with interacting and/or interfering units. In these problems, a collection of partial measurements about patterns of interaction and interference (e.g., social structure and familial relations) is available, in addition to more traditional measurements about unit-level outcomes and covariates. Formal statistical models for the analysis of this type of data have emerged as a major topic of interest in diverse areas of study. In this talk, I will review a few ideas and open areas of research that are central to this burgeoning literature, placing emphasis on inference and other core statistical issues. Then I will turn to describing a technical notion of non-ignorability that applies to sampling designs that leverage social structure, an inference strategy that can be used to obtain valid estimates in these settings, and a randomization-based approach to estimating the causal effect of peer influence, with hints to applications to advertising on social media platforms, politics and healthcare in which these statistical problems arise.

Bio: Edoardo Airoldi received his Ph.D. from Carnegie Mellon in 2006. His dissertation introduced statistical and computational elements of graph theory that support data analysis of complex systems and their evolution. Airoldi's research interests encompass statistical methodology and theory with application to molecular biology and integrative genomics, computational social science, and statistical analysis of large biological and information networks. Specific areas of technical interest include probabilistic algorithms, approximation theorems, convex and combinatorial optimization, and geometry. 

For information about the future events at IACS, see http://iacs.seas.harvard.edu/events.

********

Also of interest to the IACS community:

Harvard Department of Physics Condensed Matter Physics Seminar
Thursday, Nov. 8, 1 pm
Lyman 425

Sauro Succi
Instituto Applicazioni Calcolo, Rome Italy
Lattice Boltzmann simulation of complex flows across scales: from fluid turbulence to biopolymer translocation

Abstract:
The Lattice Boltzmann (LB) equation is a minimal form of Boltzmann kinetic equation, which is meant to describe the dynamic behaviour of fluid flows without directly solving the equations of continuum fluid mechanics. Instead, macroscopic fluid behavior is analyzed as it emerges from the underlying dynamics of a representative ensemble of particles, whose dynamics is confined to a regular phase-space-time lattice, with sufficient symmetry to recover the correct macroscopic hydrodynamic equations. Initially intended as an alternative to discretization of the Navier-Stokes equations of continuum fluid mechanics, in the last decade the LB equation has made proof of an amazing versatility, straddling across a broad range of scales of fluid motion, from fully developed turbulence, all the way down to nanoscopic flows of biological interest, and even quantum fluids. In this Seminar, we shall discuss the basic notions behind the LB theory, and present selected applications from current research in the field, such as the modeling of fluid turbulence, the rheology of soft-glassy materials and biopolymer translocation across nanopores.