🤖 AI Summary
This paper addresses the challenge of identifying socially disruptive policies—interventions that substantially alter interpersonal social network connections and induce structural fractures. Existing methods struggle to capture such latent effects. To bridge this gap, we develop the first nonparametric identification framework for social disruption, proposing a compact bound estimation method based on eigenvalues of the adjacency matrix and introducing a testable monotonicity condition to achieve point identification. Our approach integrates network analysis, matrix spectral theory, and causal inference, ensuring both theoretical rigor and empirical feasibility. Two empirical applications uncover strong social disruption effects that are severely underestimated by conventional causal evaluation methods, thereby demonstrating the framework’s superior sensitivity, identification power, and real-world applicability.
📝 Abstract
Social disruption occurs when a policy creates or destroys many network connections between agents. It is a costly side effect of many interventions and so a growing empirical literature recommends measuring and accounting for social disruption when evaluating the welfare impact of a policy. However, there is currently little work characterizing what can actually be learned about social disruption from data in practice. In this paper, we consider the problem of identifying social disruption in a research design that is popular in the literature. We provide two sets of identification results. First, we show that social disruption is not generally point identified, but informative bounds can be constructed using the eigenvalues of the network adjacency matrices observed by the researcher. Second, we show that point identification follows from a theoretically motivated monotonicity condition, and we derive a closed form representation. We apply our methods in two empirical illustrations and find large policy effects that otherwise might be missed by alternatives in the literature.
