This paper proposes a solution to the problem of the self-selection of peers in the linear-in-means model. We do not require to specify a model for how the selection of peers comes about. Rather, we exploit two restrictions that are inherent in many such specifications to construct conditional moment conditions. The restrictions in question are that link decisions that involve a given individual are not all independent of one another, but that they are independent of the link decisions made between other pairs of individuals that are located sufficiently far away in the network. These conditions imply that instrumental variables can be constructed from leave-own-out networks.
instrumental variable; linear-in-means model; network; self-selection;
- C31: Cross-Sectional Models • Spatial Models • Treatment Effect Models • Quantile Regressions • Social Interaction Models
- C36: Instrumental Variables (IV) Estimation
TSE Working Paper, n. 22-1348, July 2022