Peer effect analysis with latent processes

TL;DR

This paper introduces a novel method for analyzing peer effects from irreversible decisions using latent process modeling, providing a likelihood-based approach that overcomes limitations of traditional regression methods.

Contribution

It develops a new continuous-time latent process model for peer effects, enabling causal inference without relying on social equilibrium assumptions.

Findings

Closed-form likelihood expression derived

Method can distinguish endogenous, contextual, and correlated effects

Applicable to multiple network structures and large networks

Abstract

I study peer effects that arise from irreversible decisions in the absence of a standard social equilibrium. I model a latent sequence of decisions in continuous time and obtain a closed-form expression for the likelihood, which allows to estimate proposed causal estimands. The method avoids linear-in-means regression by modeling the (possibly unobserved) realized direction of causality, whose probability is identified. I provide identification and estimation results under two settings, several networks and one large network, while allowing for various forms of peer effect heterogeneity. Under (strong) data requirements, it is possible to separate endogenous, contextual, and correlated effects while allowing for full heterogeneity and maximum likelihood methods where parameters lend themselves to standard inference.