Working Papers

A Comparison of Approaches to Advertising Measurement: Evidence from Big Field Experiments at Facebook

Brett R. Gordon, Florian Zettelmeyer, Neha Bhargava, and Dan Chapsky

May 14, 2018

Are observational methods using good individual-level data “good enough” for ad measurement? Using data from 15 U.S. ad experiments at Facebook, this study showed that current matching and regression-based methods overestimated effectiveness relative to the randomized controlled trials. In half of studies, the estimated percentage increase in purchase outcomes was off by a factor of three across all methods.

By using MSI.org you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.