Causal Inference under Interference and Bipartite Settings

We study inference for causal effects in settings characterized by interference, arising when the outcome of a unit (e.g., patient’s infection) depends not only on their own treatment (e.g., vaccination) but also on the treatment of others (e.g., friends). We further focus on important but nonstandard settings having two distinct sets of units: units to which the intervention is applied and units on which the outcomes are measured. We call this bipartite interference: treatments applied to one intervention unit can affect multiple outcome units, and the outcome of a unit may depend on the treatments applied to multiple intervention units.