Exploiting network information to disentangle spillover effects in a field experiment on teens' museum attendance

TL;DR

This paper develops a Bayesian method combining principal stratification and causal mediation to disentangle spillover effects from other causal channels in a field experiment on teens' museum attendance, accounting for non-compliance and network influences.

Contribution

It introduces a novel Bayesian framework that integrates principal stratification and causal mediation to identify and estimate spillover effects in clustered encouragement designs.

Findings

Successfully disentangled spillover effects from other causal pathways.

Provided a formal definition of principal natural and controlled effects.

Applied the method to real data from a museum attendance experiment.

Abstract

A key element in the education of youths is their sensitization to historical and artistic heritage. We analyze a field experiment conducted in Florence (Italy) to assess how appropriate incentives assigned to high-school classes may induce teens to visit museums in their free time. Non-compliance and spillover effects make the impact evaluation of this clustered encouragement design challenging. We propose to blend principal stratification and causal mediation, by defining sub-populations of units according to their compliance behavior and using the information on their friendship networks as mediator. We formally define principal natural direct and indirect effects and principal controlled direct and spillover effects, and use them to disentangle spillovers from other causal channels. We adopt a Bayesian approach for inference.