Estimating Average Causal Effects Under Interference Between Units

This paper presents a randomization-based framework for estimating causal effects under interference between units. We develop the case of estimating average unit-level causal effects from a randomized experiment with interference of arbitrary but known form. We illustrate and assess empirical performance with a naturalistic simulation using network data from American high schools. We discuss other applications and sketch approaches for situations where there is uncertainty about the form of interference.