A0600
Title: Peer effects with misspecified peer groups
Authors: Christiern Rose - University of Queensland (Australia) [presenting]
Lizi Yu - University of Queensland (Australia)
Abstract: The purpose is to consider the identification of peer effects under peer group mispecification. Two leading cases are missing data and peer group uncertainty. Missing data can take the form of some individuals being entirely absent from the data. The researcher does not need to have any information on missing individuals and does not even need to know that they are missing. It is shown that peer effects are nevertheless identifiable under mild restrictions on the probabilities of observing individuals, and a GMM estimator is proposed to estimate the peer effects. In practice, this means that the researcher only needs to have access to an individual-level sample with group identifiers, rather than a sample of groups. Group uncertainty arises when the relevant peer group for the outcome under study is unknown. It is shown that peer effects are nevertheless identifiable if the candidate groups are nested within one another, and a non-linear least squares estimator is proposed. A Monte-Carlo experiment is conducted to demonstrate the identification results and the performance of the proposed estimators, and the method is applied to study peer effects in the career decisions of junior lawyers.
