Working Paper: CEPR ID: DP5865
Authors: Laurent Davezies; Xavier Dhaultfoeuille; Denis Fougre
Abstract: This paper considers the semiparametric identification of endogenous and exogenous peer effects based on group size variation. We show that Lee (2006)?s linear-in-means model is generically identified, even when all members of the group are not observed. While unnecessary in general, homoskedasticity may be required in special cases to recover all parameters. Extensions to asymmetric responses to peers and binary outcomes are also considered. Once more, most parameters are semiparametrically identified under weak conditions. However, recovering all of them requires more stringent assumptions. Eventually, we bring theoretical evidence that the model is more adapted to small groups.
Keywords: linear-in-means model; semiparametric identification; social interactions
JEL Codes: C14; C21; C25
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Knowledge of group sizes (C92) | Identification of peer effects (C92) |
| Variation in group sizes (C92) | Identification of peer effects (C92) |
| Weak conditions (C62) | Identification of most parameters (C51) |
| Stricter assumptions (C51) | Recovery of all parameters (C29) |
| Asymmetric responses to peers (C92) | Identification of parameters (C51) |
| Model for small groups (C92) | Understanding peer effects (C92) |