Weak Identification in Peer Effects Estimation

TL;DR

This paper investigates the challenges of estimating peer effects in growing networks, revealing biases in standard methods and proposing alternative models that mitigate these issues under certain network conditions.

Contribution

It demonstrates the limitations of average-based peer effect estimators in large networks and advocates for sum-based models to achieve reliable estimation.

Findings

Standard estimators suffer from bias or slow convergence in large networks.

Average-based models face collinearity issues as network size grows.

Sum-based models remain consistent if network degrees vary sufficiently.

Abstract

It is commonly accepted that some phenomena are social: for example, individuals' smoking habits often correlate with those of their peers. Such correlations can have a variety of explanations, such as direct contagion or shared socioeconomic circumstances. The network linear-in-means model is a workhorse statistical model which incorporates these peer effects by including average neighborhood characteristics as regressors. Although the model's parameters are identifiable under mild structural conditions on the network, it remains unclear whether identification ensures reliable estimation in the "infill" asymptotic setting, where a single network grows in size. We show that when covariates are i.i.d. and the average network degree of nodes increases with the population size, standard estimators suffer from bias or slow convergence rates due to asymptotic collinearity induced by network averaging. As an alternative, we demonstrate that linear-in-sums models, which are based on aggregate rather than average neighborhood characteristics, do not exhibit such issues as long as the network degrees have some nontrivial variation, a condition satisfied by most network models.