When: Friday, March 27, 3:00 PM
Where: Tyler 055

Abstract
In many empirical settings, individuals are interconnected, and an individual’s outcome may depend on the treatment of others, leading to interference. When interference is heterogeneous, treating individuals with specific characteristics can influence the population average outcome differently, either through their direct response or their impact on others. In setting with constrained resources where treatment, e.g., vaccination, cannot be assigned to the whole population, policymakers may leverage these heterogeneous direct and spillover effects to maximize the effectiveness of a policy by optimizing the assignment of treatment, e.g., by vaccinating individuals identified as superspreaders. Unlike no-interference settings, we show that under interference optimal treatment rules may be stochastic. Under heterogeneous clustered interference, we also propose a method to estimate optimal stochastic treatment allocations, in which an individual’s treatment probability is determined by both individual- and cluster-level covariates. The method is applied to two policies: a water, sanitation, and hygiene (WASH) intervention in Senegal and a conditional cash transfer in Colombia.

Bio
Laura Forastiere is an Associate Professor in the Department of Biostatistics at Yale School of Public Health. Her methodological research is focused on methods for assessing causal inference for evidence-based research, exploring the mechanisms underlying the effect of an intervention including causal pathways through intermediate variables or mechanisms of peer influence and spillover between connected units. Her research explores modeling, inferential, and other methodological issues that often arise in applied problems with complex clustered and network data, and standard statistical theory and methods are no longer adequate to support the goals of the analysis. Laura is eager to apply advanced statistical methodology to provide evidence on effective strategies to improve the health and wellbeing of vulnerable populations. She is particularly interested in exploring behavioral interventions that, relying on theories of behavioral economics and social psychology, exploit social interactions and peer influence among individuals. She is involved in many program evaluations and research studies in low- and middle-income countries on malaria, HIV and other STDs, maternal and child health, nutrition, cognitive development, health insurance and microcredit.