Identification of a Rank-dependent Peer Effect Model

TL;DR

This paper introduces a novel rank-dependent peer effect model that accounts for heterogeneity and distributional aspects of peer influences, providing a more nuanced understanding of how peer outcomes affect individual performance.

Contribution

The paper develops a new model capturing heterogeneity in peer effects based on ordered outcomes, with proven uniqueness, tractability, and application to real educational data.

Findings

Higher-performing friends significantly influence GPA spillovers.

The model demonstrates good finite sample performance in simulations.

Application reveals the importance of peer outcome distribution in educational settings.

Abstract

We develop a model that captures peer effect heterogeneity by modeling the endogenous spillover to be linear in ordered peer outcomes. Unlike the canonical linear-in-means model, our approach accounts for the distribution of peer outcomes as well as the size of peer groups. Under a minimal condition, our model admits a unique equilibrium and is therefore tractable and identified. Simulations show our estimator has good finite sample performance. Finally, we apply our model to educational data from Norway, finding that higher-performing friends disproportionately drive GPA spillovers. Our framework provides new insights into the structure of peer effects beyond aggregate measures.