Inferno: A Guide to Field Experiments in Online Display Advertising
30 Pages Posted: 15 May 2020
Date Written: April 20, 2020
Online display advertising is a hostile medium for field experiments. Display ad effects are tiny and necessitate large-scale experiments. The experimenter has limited control because ad exposure is jointly determined by advertisers, users, algorithms, and market competition. As such, online display ads provide useful lessons for experimenters at the frontier of digital research more generally. Display ad experiments place renewed focus on old topics like statistical power and compliance as well as on new issues like identity fragmentation and market spillovers. In this guide, we review challenges and best practices in this setting. New developments employ frontier econometric methods including causal machine learning and continuous-time modeling of dynamic treatment effects.
Keywords: field experiments, advertising effectiveness, digital advertising
JEL Classification: C93, M37
Suggested Citation: Suggested Citation