Identification and estimation of treatment and interference effects in observational studies on networks

Causal inference on a population of units connected through a network often presents technical challenges, including how to account for interference. In the presence of in- terference, for instance, potential outcomes of a unit depend on its treatment as well as on the treatments of other units, such as its neighbors in the network. In observational studies, a further complication is that the typical unconfoundedness assumption must be extended|say, to include the treatment of neighbors, and individual and neighbor- hood covariates|to guarantee identication and valid inference. Here, we propose new estimands that dene treatment and interference eects. We then derive analytical ex- pressions for the bias of a naive estimator that wrongly assumes away interference. The bias depends on the level of interference but also on the degree of association between individual and neighborhood treatments. We propose an extended unconfoundedness assumption that accounts for interference, and we develop new covariate-adjustment methods that lead to valid estimates of treatment and interference eects in obser- vational studies on networks. Estimation is based on a generalized propensity score that balances individual and neighborhood covariates across units under dierent lev- els of individual treatment and of exposure to neighbors' treatment. We carry out simulations, calibrated using friendship networks and covariates in a nationally rep- resentative longitudinal study of adolescents in grades 7-12, in the United States, to explore nite-sample performance in dierent realistic settings.