When: Friday, April 10, 3:00 PM
Where: Tyler 055

Abstract
Environmental epidemiologists are increasingly interested in establishing causality between exposures and health outcomes. A popular model for causal inference is the Rubin Causal Model (RCM). An important assumption under RCM is no interference, that is, the potential outcomes of one unit in the study are not affected by the exposure status of other units. In air pollution epidemiology this assumption is typically violated as we expect pollution upwind to affect downwind or nearby locations. In this talk, we present a methodological framework for estimating causal effects in the presence of interference by integrating social network theory into the Rubin Causal Model (RCM). We evaluate the framework’s performance through simulation studies and outline how it can be used to evaluate environmental policy.

Bio
Anny-Claude Joseph is a faculty member in the Department of Mathematics and Statistics at Wellesley College, where she teaches across the statistics and data science curriculum. She earned her PhD from Virginia Commonwealth University and brings experience from over 20 years in the classroom. Her research focuses on biostatistics and public health, with an emphasis on using statistical modeling to better understand the relationship between health and the physical environment, as well as applying analytical methods to improve health outcomes for mothers and children.