Working Paper: CEPR ID: DP14386
Authors: Marcel Fafchamps; Bet Caeyers
Abstract: We examine a largely unexplored source of downward bias in peer effect estimation, namely, exclusion bias. We derive formulas for the magnitude of the bias in tests of random peer assignment, and for the combined reflection and exclusion bias in peer effect estimation. We show how to consistently test random peer assignment and how to estimate and conduct consistent inference on peer effects without instruments. The method corrects for the presence of reflection and exclusion bias but imposes restrictions on correlated effects. It allows the joint estimation of endogenous and exogenous peer effects in situations where instruments are not available and cannot be constructed from the network matrix. We estimate endogenous and exogenous peer effects in two datasets where instrumental approaches fail because peer assignment is to mutually exclusive groups of identical size. We find significant evidence of positive peer effects in one, negative peer effects in the other. In both cases, ignoring exclusion bias would have led to incorrect inference. We also demonstrate how the same approach applies to autoregressive models.
Keywords: exclusion bias; peer effects; reflection bias; random peer assignment; social interactions; linear-in-means; autoregressive models
JEL Codes: C32
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| exclusion bias (J15) | downward bias in the estimation of peer effects (C92) |
| individuals cannot be their own peers in a selection pool (C92) | exclusion bias (J15) |
| ignoring exclusion bias (C24) | incorrect inferences about peer effects (C92) |
| reflection bias (D91) | inflated estimates of peer effects (C92) |
| exclusion bias (J15) | negative direction of peer effects (C92) |
| method allows for joint estimation of endogenous and exogenous peer effects (C92) | consistent estimates (C51) |